---
_id: '63710'
author:
- first_name: Gjorgjina
full_name: Cenikj, Gjorgjina
last_name: Cenikj
- first_name: Gasper
full_name: Petelin, Gasper
last_name: Petelin
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Nikola
full_name: Cenikj, Nikola
last_name: Cenikj
- first_name: Tome
full_name: Eftimov, Tome
last_name: Eftimov
citation:
ama: 'Cenikj G, Petelin G, Seiler M, Cenikj N, Eftimov T. Landscape features in
single-objective continuous optimization: Have we hit a wall in algorithm selection
generalization? Swarm Evol Comput. 2025;94:101894. doi:10.1016/J.SWEVO.2025.101894'
apa: 'Cenikj, G., Petelin, G., Seiler, M., Cenikj, N., & Eftimov, T. (2025).
Landscape features in single-objective continuous optimization: Have we hit a
wall in algorithm selection generalization? Swarm Evol. Comput., 94,
101894. https://doi.org/10.1016/J.SWEVO.2025.101894'
bibtex: '@article{Cenikj_Petelin_Seiler_Cenikj_Eftimov_2025, title={Landscape features
in single-objective continuous optimization: Have we hit a wall in algorithm selection
generalization?}, volume={94}, DOI={10.1016/J.SWEVO.2025.101894},
journal={Swarm Evol. Comput.}, author={Cenikj, Gjorgjina and Petelin, Gasper and
Seiler, Moritz and Cenikj, Nikola and Eftimov, Tome}, year={2025}, pages={101894}
}'
chicago: 'Cenikj, Gjorgjina, Gasper Petelin, Moritz Seiler, Nikola Cenikj, and Tome
Eftimov. “Landscape Features in Single-Objective Continuous Optimization: Have
We Hit a Wall in Algorithm Selection Generalization?” Swarm Evol. Comput.
94 (2025): 101894. https://doi.org/10.1016/J.SWEVO.2025.101894.'
ieee: 'G. Cenikj, G. Petelin, M. Seiler, N. Cenikj, and T. Eftimov, “Landscape features
in single-objective continuous optimization: Have we hit a wall in algorithm selection
generalization?,” Swarm Evol. Comput., vol. 94, p. 101894, 2025, doi: 10.1016/J.SWEVO.2025.101894.'
mla: 'Cenikj, Gjorgjina, et al. “Landscape Features in Single-Objective Continuous
Optimization: Have We Hit a Wall in Algorithm Selection Generalization?” Swarm
Evol. Comput., vol. 94, 2025, p. 101894, doi:10.1016/J.SWEVO.2025.101894.'
short: G. Cenikj, G. Petelin, M. Seiler, N. Cenikj, T. Eftimov, Swarm Evol. Comput.
94 (2025) 101894.
date_created: 2026-01-22T14:57:35Z
date_updated: 2026-01-22T14:58:13Z
doi: 10.1016/J.SWEVO.2025.101894
intvolume: ' 94'
language:
- iso: eng
page: '101894'
publication: Swarm Evol. Comput.
status: public
title: 'Landscape features in single-objective continuous optimization: Have we hit
a wall in algorithm selection generalization?'
type: journal_article
user_id: '15504'
volume: 94
year: '2025'
...
---
_id: '60220'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Kerschke P, Trautmann H. Deep-ELA: Deep Exploratory Landscape Analysis
with Self-Supervised Pretrained Transformers for Single- and Multi-Objective Continuous
Optimization Problems . Evolutionary Computation. Published online 2025:1-27.
doi:https://doi.org/10.1162/evco_a_00367'
apa: 'Seiler, M., Kerschke, P., & Trautmann, H. (2025). Deep-ELA: Deep Exploratory
Landscape Analysis with Self-Supervised Pretrained Transformers for Single- and
Multi-Objective Continuous Optimization Problems . Evolutionary Computation,
1–27. https://doi.org/10.1162/evco_a_00367'
bibtex: '@article{Seiler_Kerschke_Trautmann_2025, title={Deep-ELA: Deep Exploratory
Landscape Analysis with Self-Supervised Pretrained Transformers for Single- and
Multi-Objective Continuous Optimization Problems }, DOI={https://doi.org/10.1162/evco_a_00367},
journal={Evolutionary Computation}, author={Seiler, Moritz and Kerschke, Pascal
and Trautmann, Heike}, year={2025}, pages={1–27} }'
chicago: 'Seiler, Moritz, Pascal Kerschke, and Heike Trautmann. “Deep-ELA: Deep
Exploratory Landscape Analysis with Self-Supervised Pretrained Transformers for
Single- and Multi-Objective Continuous Optimization Problems .” Evolutionary
Computation, 2025, 1–27. https://doi.org/10.1162/evco_a_00367.'
ieee: 'M. Seiler, P. Kerschke, and H. Trautmann, “Deep-ELA: Deep Exploratory Landscape
Analysis with Self-Supervised Pretrained Transformers for Single- and Multi-Objective
Continuous Optimization Problems ,” Evolutionary Computation, pp. 1–27,
2025, doi: https://doi.org/10.1162/evco_a_00367.'
mla: 'Seiler, Moritz, et al. “Deep-ELA: Deep Exploratory Landscape Analysis with
Self-Supervised Pretrained Transformers for Single- and Multi-Objective Continuous
Optimization Problems .” Evolutionary Computation, 2025, pp. 1–27, doi:https://doi.org/10.1162/evco_a_00367.'
short: M. Seiler, P. Kerschke, H. Trautmann, Evolutionary Computation (2025) 1–27.
date_created: 2025-06-16T12:20:20Z
date_updated: 2025-06-16T12:24:15Z
department:
- _id: '819'
doi: https://doi.org/10.1162/evco_a_00367
language:
- iso: eng
page: 1-27
publication: Evolutionary Computation
status: public
title: 'Deep-ELA: Deep Exploratory Landscape Analysis with Self-Supervised Pretrained
Transformers for Single- and Multi-Objective Continuous Optimization Problems '
type: journal_article
user_id: '15504'
year: '2025'
...
---
_id: '60813'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Oliver Ludger
full_name: Preuß, Oliver Ludger
id: '102978'
last_name: Preuß
orcid: 0009-0008-9308-2418
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Preuß OL, Trautmann H. RandOptGen: A Unified Random Problem Generator
for Single- and Multi-Objective Optimization Problems with Mixed-Variable Input
Spaces. In: Filipic B, ed. Proceedings of the Genetic and Evolutionary Computation
Conference, GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025.
ACM; 2025:76–84. doi:10.1145/3712256.3726478'
apa: 'Seiler, M., Preuß, O. L., & Trautmann, H. (2025). RandOptGen: A Unified
Random Problem Generator for Single- and Multi-Objective Optimization Problems
with Mixed-Variable Input Spaces. In B. Filipic (Ed.), Proceedings of the Genetic
and Evolutionary Computation Conference, GECCO 2025, NH Malaga Hotel, Malaga,
Spain, July 14-18, 2025 (pp. 76–84). ACM. https://doi.org/10.1145/3712256.3726478'
bibtex: '@inproceedings{Seiler_Preuß_Trautmann_2025, title={RandOptGen: A Unified
Random Problem Generator for Single- and Multi-Objective Optimization Problems
with Mixed-Variable Input Spaces}, DOI={10.1145/3712256.3726478},
booktitle={Proceedings of the Genetic and Evolutionary Computation Conference,
GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025}, publisher={ACM},
author={Seiler, Moritz and Preuß, Oliver Ludger and Trautmann, Heike}, editor={Filipic,
Bogdan}, year={2025}, pages={76–84} }'
chicago: 'Seiler, Moritz, Oliver Ludger Preuß, and Heike Trautmann. “RandOptGen:
A Unified Random Problem Generator for Single- and Multi-Objective Optimization
Problems with Mixed-Variable Input Spaces.” In Proceedings of the Genetic and
Evolutionary Computation Conference, GECCO 2025, NH Malaga Hotel, Malaga, Spain,
July 14-18, 2025, edited by Bogdan Filipic, 76–84. ACM, 2025. https://doi.org/10.1145/3712256.3726478.'
ieee: 'M. Seiler, O. L. Preuß, and H. Trautmann, “RandOptGen: A Unified Random Problem
Generator for Single- and Multi-Objective Optimization Problems with Mixed-Variable
Input Spaces,” in Proceedings of the Genetic and Evolutionary Computation Conference,
GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025, 2025, pp. 76–84,
doi: 10.1145/3712256.3726478.'
mla: 'Seiler, Moritz, et al. “RandOptGen: A Unified Random Problem Generator for
Single- and Multi-Objective Optimization Problems with Mixed-Variable Input Spaces.”
Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2025,
NH Malaga Hotel, Malaga, Spain, July 14-18, 2025, edited by Bogdan Filipic,
ACM, 2025, pp. 76–84, doi:10.1145/3712256.3726478.'
short: 'M. Seiler, O.L. Preuß, H. Trautmann, in: B. Filipic (Ed.), Proceedings of
the Genetic and Evolutionary Computation Conference, GECCO 2025, NH Malaga Hotel,
Malaga, Spain, July 14-18, 2025, ACM, 2025, pp. 76–84.'
date_created: 2025-07-29T06:12:57Z
date_updated: 2025-07-29T06:13:43Z
department:
- _id: '819'
doi: 10.1145/3712256.3726478
editor:
- first_name: Bogdan
full_name: Filipic, Bogdan
last_name: Filipic
language:
- iso: eng
page: 76–84
publication: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO
2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025
publisher: ACM
status: public
title: 'RandOptGen: A Unified Random Problem Generator for Single- and Multi-Objective
Optimization Problems with Mixed-Variable Input Spaces'
type: conference
user_id: '15504'
year: '2025'
...
---
_id: '60814'
author:
- first_name: Elias
full_name: Schede, Elias
last_name: Schede
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Kevin
full_name: Tierney, Kevin
last_name: Tierney
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Schede E, Seiler M, Tierney K, Trautmann H. Deep reinforcement learning for
instance-specific algorithm configuration (GECCO Best Paper Award). In: Filipic
B, ed. Proceedings of the Genetic and Evolutionary Computation Conference,
GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025. ACM; 2025:1190–1198.
doi:10.1145/3712256.3726480'
apa: Schede, E., Seiler, M., Tierney, K., & Trautmann, H. (2025). Deep reinforcement
learning for instance-specific algorithm configuration (GECCO Best Paper Award).
In B. Filipic (Ed.), Proceedings of the Genetic and Evolutionary Computation
Conference, GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025 (pp.
1190–1198). ACM. https://doi.org/10.1145/3712256.3726480
bibtex: '@inproceedings{Schede_Seiler_Tierney_Trautmann_2025, title={Deep reinforcement
learning for instance-specific algorithm configuration (GECCO Best Paper Award)},
DOI={10.1145/3712256.3726480},
booktitle={Proceedings of the Genetic and Evolutionary Computation Conference,
GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025}, publisher={ACM},
author={Schede, Elias and Seiler, Moritz and Tierney, Kevin and Trautmann, Heike},
editor={Filipic, Bogdan}, year={2025}, pages={1190–1198} }'
chicago: Schede, Elias, Moritz Seiler, Kevin Tierney, and Heike Trautmann. “Deep
Reinforcement Learning for Instance-Specific Algorithm Configuration (GECCO Best
Paper Award).” In Proceedings of the Genetic and Evolutionary Computation Conference,
GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025, edited by Bogdan
Filipic, 1190–1198. ACM, 2025. https://doi.org/10.1145/3712256.3726480.
ieee: 'E. Schede, M. Seiler, K. Tierney, and H. Trautmann, “Deep reinforcement learning
for instance-specific algorithm configuration (GECCO Best Paper Award),” in Proceedings
of the Genetic and Evolutionary Computation Conference, GECCO 2025, NH Malaga
Hotel, Malaga, Spain, July 14-18, 2025, 2025, pp. 1190–1198, doi: 10.1145/3712256.3726480.'
mla: Schede, Elias, et al. “Deep Reinforcement Learning for Instance-Specific Algorithm
Configuration (GECCO Best Paper Award).” Proceedings of the Genetic and Evolutionary
Computation Conference, GECCO 2025, NH Malaga Hotel, Malaga, Spain, July 14-18,
2025, edited by Bogdan Filipic, ACM, 2025, pp. 1190–1198, doi:10.1145/3712256.3726480.
short: 'E. Schede, M. Seiler, K. Tierney, H. Trautmann, in: B. Filipic (Ed.), Proceedings
of the Genetic and Evolutionary Computation Conference, GECCO 2025, NH Malaga
Hotel, Malaga, Spain, July 14-18, 2025, ACM, 2025, pp. 1190–1198.'
date_created: 2025-07-29T06:14:03Z
date_updated: 2025-07-29T12:17:30Z
department:
- _id: '819'
doi: 10.1145/3712256.3726480
editor:
- first_name: Bogdan
full_name: Filipic, Bogdan
last_name: Filipic
language:
- iso: eng
page: 1190–1198
publication: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO
2025, NH Malaga Hotel, Malaga, Spain, July 14-18, 2025
publisher: ACM
status: public
title: Deep reinforcement learning for instance-specific algorithm configuration (GECCO
Best Paper Award)
type: conference
user_id: '100740'
year: '2025'
...
---
_id: '52749'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Jeroen
full_name: Rook, Jeroen
last_name: Rook
- first_name: Jonathan
full_name: Heins, Jonathan
last_name: Heins
- first_name: Oliver Ludger
full_name: Preuß, Oliver Ludger
id: '102978'
last_name: Preuß
orcid: 0009-0008-9308-2418
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Rook J, Heins J, Preuß OL, Bossek J, Trautmann H. Using Reinforcement
Learning for Per-Instance Algorithm Configuration on the TSP. In: 2023 IEEE
Symposium Series on Computational Intelligence (SSCI). IEEE; 2024. doi:10.1109/ssci52147.2023.10372008'
apa: Seiler, M., Rook, J., Heins, J., Preuß, O. L., Bossek, J., & Trautmann,
H. (2024). Using Reinforcement Learning for Per-Instance Algorithm Configuration
on the TSP. 2023 IEEE Symposium Series on Computational Intelligence (SSCI).
https://doi.org/10.1109/ssci52147.2023.10372008
bibtex: '@inproceedings{Seiler_Rook_Heins_Preuß_Bossek_Trautmann_2024, title={Using
Reinforcement Learning for Per-Instance Algorithm Configuration on the TSP}, DOI={10.1109/ssci52147.2023.10372008},
booktitle={2023 IEEE Symposium Series on Computational Intelligence (SSCI)}, publisher={IEEE},
author={Seiler, Moritz and Rook, Jeroen and Heins, Jonathan and Preuß, Oliver
Ludger and Bossek, Jakob and Trautmann, Heike}, year={2024} }'
chicago: Seiler, Moritz, Jeroen Rook, Jonathan Heins, Oliver Ludger Preuß, Jakob
Bossek, and Heike Trautmann. “Using Reinforcement Learning for Per-Instance Algorithm
Configuration on the TSP.” In 2023 IEEE Symposium Series on Computational Intelligence
(SSCI). IEEE, 2024. https://doi.org/10.1109/ssci52147.2023.10372008.
ieee: 'M. Seiler, J. Rook, J. Heins, O. L. Preuß, J. Bossek, and H. Trautmann, “Using
Reinforcement Learning for Per-Instance Algorithm Configuration on the TSP,” 2024,
doi: 10.1109/ssci52147.2023.10372008.'
mla: Seiler, Moritz, et al. “Using Reinforcement Learning for Per-Instance Algorithm
Configuration on the TSP.” 2023 IEEE Symposium Series on Computational Intelligence
(SSCI), IEEE, 2024, doi:10.1109/ssci52147.2023.10372008.
short: 'M. Seiler, J. Rook, J. Heins, O.L. Preuß, J. Bossek, H. Trautmann, in: 2023
IEEE Symposium Series on Computational Intelligence (SSCI), IEEE, 2024.'
date_created: 2024-03-25T08:15:01Z
date_updated: 2024-06-10T11:59:44Z
department:
- _id: '819'
doi: 10.1109/ssci52147.2023.10372008
language:
- iso: eng
publication: 2023 IEEE Symposium Series on Computational Intelligence (SSCI)
publication_status: published
publisher: IEEE
status: public
title: Using Reinforcement Learning for Per-Instance Algorithm Configuration on the
TSP
type: conference
user_id: '15504'
year: '2024'
...
---
_id: '58335'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Urban
full_name: Skvorc, Urban
id: '103764'
last_name: Skvorc
- first_name: Carola
full_name: Doerr, Carola
last_name: Doerr
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Skvorc U, Doerr C, Trautmann H. Synergies of Deep and Classical
Exploratory Landscape Features for Automated Algorithm Selection. In: Festa P,
Ferone D, Pastore T, Pisacane O, eds. Learning and Intelligent Optimization
- 18th International Conference, LION 18, Ischia Island, Italy, June 9-13, 2024,
Revised Selected Papers. Vol 14990. Lecture Notes in Computer Science. Springer;
2024:361–376. doi:10.1007/978-3-031-75623-8_29'
apa: Seiler, M., Skvorc, U., Doerr, C., & Trautmann, H. (2024). Synergies of
Deep and Classical Exploratory Landscape Features for Automated Algorithm Selection.
In P. Festa, D. Ferone, T. Pastore, & O. Pisacane (Eds.), Learning and
Intelligent Optimization - 18th International Conference, LION 18, Ischia Island,
Italy, June 9-13, 2024, Revised Selected Papers (Vol. 14990, pp. 361–376).
Springer. https://doi.org/10.1007/978-3-031-75623-8_29
bibtex: '@inproceedings{Seiler_Skvorc_Doerr_Trautmann_2024, series={Lecture Notes
in Computer Science}, title={Synergies of Deep and Classical Exploratory Landscape
Features for Automated Algorithm Selection}, volume={14990}, DOI={10.1007/978-3-031-75623-8_29},
booktitle={Learning and Intelligent Optimization - 18th International Conference,
LION 18, Ischia Island, Italy, June 9-13, 2024, Revised Selected Papers}, publisher={Springer},
author={Seiler, Moritz and Skvorc, Urban and Doerr, Carola and Trautmann, Heike},
editor={Festa, Paola and Ferone, Daniele and Pastore, Tommaso and Pisacane, Ornella},
year={2024}, pages={361–376}, collection={Lecture Notes in Computer Science} }'
chicago: Seiler, Moritz, Urban Skvorc, Carola Doerr, and Heike Trautmann. “Synergies
of Deep and Classical Exploratory Landscape Features for Automated Algorithm Selection.”
In Learning and Intelligent Optimization - 18th International Conference, LION
18, Ischia Island, Italy, June 9-13, 2024, Revised Selected Papers, edited
by Paola Festa, Daniele Ferone, Tommaso Pastore, and Ornella Pisacane, 14990:361–376.
Lecture Notes in Computer Science. Springer, 2024. https://doi.org/10.1007/978-3-031-75623-8_29.
ieee: 'M. Seiler, U. Skvorc, C. Doerr, and H. Trautmann, “Synergies of Deep and
Classical Exploratory Landscape Features for Automated Algorithm Selection,” in
Learning and Intelligent Optimization - 18th International Conference, LION
18, Ischia Island, Italy, June 9-13, 2024, Revised Selected Papers, 2024,
vol. 14990, pp. 361–376, doi: 10.1007/978-3-031-75623-8_29.'
mla: Seiler, Moritz, et al. “Synergies of Deep and Classical Exploratory Landscape
Features for Automated Algorithm Selection.” Learning and Intelligent Optimization
- 18th International Conference, LION 18, Ischia Island, Italy, June 9-13, 2024,
Revised Selected Papers, edited by Paola Festa et al., vol. 14990, Springer,
2024, pp. 361–376, doi:10.1007/978-3-031-75623-8_29.
short: 'M. Seiler, U. Skvorc, C. Doerr, H. Trautmann, in: P. Festa, D. Ferone, T.
Pastore, O. Pisacane (Eds.), Learning and Intelligent Optimization - 18th International
Conference, LION 18, Ischia Island, Italy, June 9-13, 2024, Revised Selected Papers,
Springer, 2024, pp. 361–376.'
date_created: 2025-01-23T12:39:37Z
date_updated: 2025-01-23T12:40:32Z
department:
- _id: '819'
doi: 10.1007/978-3-031-75623-8_29
editor:
- first_name: Paola
full_name: Festa, Paola
last_name: Festa
- first_name: Daniele
full_name: Ferone, Daniele
last_name: Ferone
- first_name: Tommaso
full_name: Pastore, Tommaso
last_name: Pastore
- first_name: Ornella
full_name: Pisacane, Ornella
last_name: Pisacane
intvolume: ' 14990'
language:
- iso: eng
page: 361–376
publication: Learning and Intelligent Optimization - 18th International Conference,
LION 18, Ischia Island, Italy, June 9-13, 2024, Revised Selected Papers
publisher: Springer
series_title: Lecture Notes in Computer Science
status: public
title: Synergies of Deep and Classical Exploratory Landscape Features for Automated
Algorithm Selection
type: conference
user_id: '15504'
volume: 14990
year: '2024'
...
---
_id: '60132'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Urban
full_name: Skvorc, Urban
id: '103764'
last_name: Skvorc
- first_name: Gjorgjina
full_name: Cenikj, Gjorgjina
last_name: Cenikj
- first_name: Carola
full_name: Doerr, Carola
last_name: Doerr
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Skvorc U, Cenikj G, Doerr C, Trautmann H. Learned Features vs. Classical
ELA on Affine BBOB Functions. In: Affenzeller M, Winkler SM, Kononova AV, et al.,
eds. Parallel Problem Solving from Nature - PPSN XVIII - 18th International
Conference, PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings,
Part II. Vol 15149. Lecture Notes in Computer Science. Springer; 2024:137–153.
doi:10.1007/978-3-031-70068-2_9'
apa: Seiler, M., Skvorc, U., Cenikj, G., Doerr, C., & Trautmann, H. (2024).
Learned Features vs. Classical ELA on Affine BBOB Functions. In M. Affenzeller,
S. M. Winkler, A. V. Kononova, H. Trautmann, T. Tusar, P. Machado, & T. Bäck
(Eds.), Parallel Problem Solving from Nature - PPSN XVIII - 18th International
Conference, PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings,
Part II (Vol. 15149, pp. 137–153). Springer. https://doi.org/10.1007/978-3-031-70068-2_9
bibtex: '@inproceedings{Seiler_Skvorc_Cenikj_Doerr_Trautmann_2024, series={Lecture
Notes in Computer Science}, title={Learned Features vs. Classical ELA on Affine
BBOB Functions}, volume={15149}, DOI={10.1007/978-3-031-70068-2_9},
booktitle={Parallel Problem Solving from Nature - PPSN XVIII - 18th International
Conference, PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings,
Part II}, publisher={Springer}, author={Seiler, Moritz and Skvorc, Urban and Cenikj,
Gjorgjina and Doerr, Carola and Trautmann, Heike}, editor={Affenzeller, Michael
and Winkler, Stephan M. and Kononova, Anna V. and Trautmann, Heike and Tusar,
Tea and Machado, Penousal and Bäck, Thomas}, year={2024}, pages={137–153}, collection={Lecture
Notes in Computer Science} }'
chicago: Seiler, Moritz, Urban Skvorc, Gjorgjina Cenikj, Carola Doerr, and Heike
Trautmann. “Learned Features vs. Classical ELA on Affine BBOB Functions.” In Parallel
Problem Solving from Nature - PPSN XVIII - 18th International Conference, PPSN
2024, Hagenberg, Austria, September 14-18, 2024, Proceedings, Part II, edited
by Michael Affenzeller, Stephan M. Winkler, Anna V. Kononova, Heike Trautmann,
Tea Tusar, Penousal Machado, and Thomas Bäck, 15149:137–153. Lecture Notes in
Computer Science. Springer, 2024. https://doi.org/10.1007/978-3-031-70068-2_9.
ieee: 'M. Seiler, U. Skvorc, G. Cenikj, C. Doerr, and H. Trautmann, “Learned Features
vs. Classical ELA on Affine BBOB Functions,” in Parallel Problem Solving from
Nature - PPSN XVIII - 18th International Conference, PPSN 2024, Hagenberg, Austria,
September 14-18, 2024, Proceedings, Part II, 2024, vol. 15149, pp. 137–153,
doi: 10.1007/978-3-031-70068-2_9.'
mla: Seiler, Moritz, et al. “Learned Features vs. Classical ELA on Affine BBOB Functions.”
Parallel Problem Solving from Nature - PPSN XVIII - 18th International Conference,
PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings, Part II,
edited by Michael Affenzeller et al., vol. 15149, Springer, 2024, pp. 137–153,
doi:10.1007/978-3-031-70068-2_9.
short: 'M. Seiler, U. Skvorc, G. Cenikj, C. Doerr, H. Trautmann, in: M. Affenzeller,
S.M. Winkler, A.V. Kononova, H. Trautmann, T. Tusar, P. Machado, T. Bäck (Eds.),
Parallel Problem Solving from Nature - PPSN XVIII - 18th International Conference,
PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings, Part II, Springer,
2024, pp. 137–153.'
date_created: 2025-06-04T12:48:56Z
date_updated: 2025-06-04T12:49:30Z
doi: 10.1007/978-3-031-70068-2_9
editor:
- first_name: Michael
full_name: Affenzeller, Michael
last_name: Affenzeller
- first_name: Stephan M.
full_name: Winkler, Stephan M.
last_name: Winkler
- first_name: Anna V.
full_name: Kononova, Anna V.
last_name: Kononova
- first_name: Heike
full_name: Trautmann, Heike
last_name: Trautmann
- first_name: Tea
full_name: Tusar, Tea
last_name: Tusar
- first_name: Penousal
full_name: Machado, Penousal
last_name: Machado
- first_name: Thomas
full_name: Bäck, Thomas
last_name: Bäck
intvolume: ' 15149'
language:
- iso: eng
page: 137–153
publication: Parallel Problem Solving from Nature - PPSN XVIII - 18th International
Conference, PPSN 2024, Hagenberg, Austria, September 14-18, 2024, Proceedings, Part
II
publisher: Springer
series_title: Lecture Notes in Computer Science
status: public
title: Learned Features vs. Classical ELA on Affine BBOB Functions
type: conference
user_id: '15504'
volume: 15149
year: '2024'
...
---
_id: '46310'
abstract:
- lang: eng
text: 'Classic automated algorithm selection (AS) for (combinatorial) optimization
problems heavily relies on so-called instance features, i.e., numerical characteristics
of the problem at hand ideally extracted with computationally low-demanding routines.
For the traveling salesperson problem (TSP) a plethora of features have been suggested.
Most of these features are, if at all, only normalized imprecisely raising the
issue of feature values being strongly affected by the instance size. Such artifacts
may have detrimental effects on algorithm selection models. We propose a normalization
for two feature groups which stood out in multiple AS studies on the TSP: (a)
features based on a minimum spanning tree (MST) and (b) nearest neighbor relationships
of the input instance. To this end we theoretically derive minimum and maximum
values for properties of MSTs and k-nearest neighbor graphs (NNG) of Euclidean
graphs. We analyze the differences in feature space between normalized versions
of these features and their unnormalized counterparts. Our empirical investigations
on various TSP benchmark sets point out that the feature scaling succeeds in eliminating
the effect of the instance size. A proof-of-concept AS-study shows promising results:
models trained with normalized features tend to outperform those trained with
the respective vanilla features.'
author:
- first_name: Jonathan
full_name: Heins, Jonathan
last_name: Heins
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Janina
full_name: Pohl, Janina
last_name: Pohl
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
citation:
ama: Heins J, Bossek J, Pohl J, Seiler M, Trautmann H, Kerschke P. A study on the
effects of normalized TSP features for automated algorithm selection. Theoretical
Computer Science. 2023;940:123-145. doi:https://doi.org/10.1016/j.tcs.2022.10.019
apa: Heins, J., Bossek, J., Pohl, J., Seiler, M., Trautmann, H., & Kerschke,
P. (2023). A study on the effects of normalized TSP features for automated algorithm
selection. Theoretical Computer Science, 940, 123–145. https://doi.org/10.1016/j.tcs.2022.10.019
bibtex: '@article{Heins_Bossek_Pohl_Seiler_Trautmann_Kerschke_2023, title={A study
on the effects of normalized TSP features for automated algorithm selection},
volume={940}, DOI={https://doi.org/10.1016/j.tcs.2022.10.019},
journal={Theoretical Computer Science}, author={Heins, Jonathan and Bossek, Jakob
and Pohl, Janina and Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal},
year={2023}, pages={123–145} }'
chicago: 'Heins, Jonathan, Jakob Bossek, Janina Pohl, Moritz Seiler, Heike Trautmann,
and Pascal Kerschke. “A Study on the Effects of Normalized TSP Features for Automated
Algorithm Selection.” Theoretical Computer Science 940 (2023): 123–45.
https://doi.org/10.1016/j.tcs.2022.10.019.'
ieee: 'J. Heins, J. Bossek, J. Pohl, M. Seiler, H. Trautmann, and P. Kerschke, “A
study on the effects of normalized TSP features for automated algorithm selection,”
Theoretical Computer Science, vol. 940, pp. 123–145, 2023, doi: https://doi.org/10.1016/j.tcs.2022.10.019.'
mla: Heins, Jonathan, et al. “A Study on the Effects of Normalized TSP Features
for Automated Algorithm Selection.” Theoretical Computer Science, vol.
940, 2023, pp. 123–45, doi:https://doi.org/10.1016/j.tcs.2022.10.019.
short: J. Heins, J. Bossek, J. Pohl, M. Seiler, H. Trautmann, P. Kerschke, Theoretical
Computer Science 940 (2023) 123–145.
date_created: 2023-08-04T07:18:38Z
date_updated: 2024-06-10T11:57:21Z
department:
- _id: '34'
- _id: '819'
doi: https://doi.org/10.1016/j.tcs.2022.10.019
intvolume: ' 940'
keyword:
- Feature normalization
- Algorithm selection
- Traveling salesperson problem
language:
- iso: eng
page: 123-145
publication: Theoretical Computer Science
publication_identifier:
issn:
- 0304-3975
status: public
title: A study on the effects of normalized TSP features for automated algorithm selection
type: journal_article
user_id: '15504'
volume: 940
year: '2023'
...
---
_id: '48898'
abstract:
- lang: eng
text: 'Automated Algorithm Configuration (AAC) usually takes a global perspective:
it identifies a parameter configuration for an (optimization) algorithm that maximizes
a performance metric over a set of instances. However, the optimal choice of parameters
strongly depends on the instance at hand and should thus be calculated on a per-instance
basis. We explore the potential of Per-Instance Algorithm Configuration (PIAC)
by using Reinforcement Learning (RL). To this end, we propose a novel PIAC approach
that is based on deep neural networks. We apply it to predict configurations for
the Lin\textendash Kernighan heuristic (LKH) for the Traveling Salesperson Problem
(TSP) individually for every single instance. To train our PIAC approach, we create
a large set of 100000 TSP instances with 2000 nodes each \textemdash currently
the largest benchmark set to the best of our knowledge. We compare our approach
to the state-of-the-art AAC method Sequential Model-based Algorithm Configuration
(SMAC). The results show that our PIAC approach outperforms this baseline on both
the newly created instance set and established instance sets.'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Jeroen
full_name: Rook, Jeroen
last_name: Rook
- first_name: Jonathan
full_name: Heins, Jonathan
last_name: Heins
- first_name: Oliver Ludger
full_name: Preuß, Oliver Ludger
id: '102978'
last_name: Preuß
orcid: 0009-0008-9308-2418
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Rook J, Heins J, Preuß OL, Bossek J, Trautmann H. Using Reinforcement
Learning for Per-Instance Algorithm Configuration on the TSP. In: 2023 IEEE
Symposium Series on Computational Intelligence (SSCI). ; :361-368. doi:10.1109/SSCI52147.2023.10372008'
apa: Seiler, M., Rook, J., Heins, J., Preuß, O. L., Bossek, J., & Trautmann,
H. (n.d.). Using Reinforcement Learning for Per-Instance Algorithm Configuration
on the TSP. 2023 IEEE Symposium Series on Computational Intelligence (SSCI),
361–368. https://doi.org/10.1109/SSCI52147.2023.10372008
bibtex: '@inproceedings{Seiler_Rook_Heins_Preuß_Bossek_Trautmann, title={Using Reinforcement
Learning for Per-Instance Algorithm Configuration on the TSP}, DOI={10.1109/SSCI52147.2023.10372008},
booktitle={2023 IEEE Symposium Series on Computational Intelligence (SSCI)}, author={Seiler,
Moritz and Rook, Jeroen and Heins, Jonathan and Preuß, Oliver Ludger and Bossek,
Jakob and Trautmann, Heike}, pages={361–368} }'
chicago: Seiler, Moritz, Jeroen Rook, Jonathan Heins, Oliver Ludger Preuß, Jakob
Bossek, and Heike Trautmann. “Using Reinforcement Learning for Per-Instance Algorithm
Configuration on the TSP.” In 2023 IEEE Symposium Series on Computational Intelligence
(SSCI), 361–68, n.d. https://doi.org/10.1109/SSCI52147.2023.10372008.
ieee: 'M. Seiler, J. Rook, J. Heins, O. L. Preuß, J. Bossek, and H. Trautmann, “Using
Reinforcement Learning for Per-Instance Algorithm Configuration on the TSP,” in
2023 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 361–368,
doi: 10.1109/SSCI52147.2023.10372008.'
mla: Seiler, Moritz, et al. “Using Reinforcement Learning for Per-Instance Algorithm
Configuration on the TSP.” 2023 IEEE Symposium Series on Computational Intelligence
(SSCI), pp. 361–68, doi:10.1109/SSCI52147.2023.10372008.
short: 'M. Seiler, J. Rook, J. Heins, O.L. Preuß, J. Bossek, H. Trautmann, in: 2023
IEEE Symposium Series on Computational Intelligence (SSCI), n.d., pp. 361–368.'
date_created: 2023-11-14T15:59:01Z
date_updated: 2024-06-10T11:56:58Z
department:
- _id: '819'
doi: 10.1109/SSCI52147.2023.10372008
extern: '1'
language:
- iso: eng
page: 361 - 368
publication: 2023 IEEE Symposium Series on Computational Intelligence (SSCI)
publication_status: accepted
status: public
title: Using Reinforcement Learning for Per-Instance Algorithm Configuration on the
TSP
type: conference
user_id: '15504'
year: '2023'
...
---
_id: '46307'
abstract:
- lang: eng
text: Exploratory Landscape Analysis is a powerful technique for numerically characterizing
landscapes of single-objective continuous optimization problems. Landscape insights
are crucial both for problem understanding as well as for assessing benchmark
set diversity and composition. Despite the irrefutable usefulness of these features,
they suffer from their own ailments and downsides. Hence, in this work we provide
a collection of different approaches to characterize optimization landscapes.
Similar to conventional landscape features, we require a small initial sample.
However, instead of computing features based on that sample, we develop alternative
representations of the original sample. These range from point clouds to 2D images
and, therefore, are entirely feature-free. We demonstrate and validate our devised
methods on the BBOB testbed and predict, with the help of Deep Learning, the high-level,
expert-based landscape properties such as the degree of multimodality and the
existence of funnel structures. The quality of our approaches is on par with methods
relying on the traditional landscape features. Thereby, we provide an exciting
new perspective on every research area which utilizes problem information such
as problem understanding and algorithm design as well as automated algorithm configuration
and selection.
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Raphael Patrick
full_name: Prager, Raphael Patrick
last_name: Prager
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Prager RP, Kerschke P, Trautmann H. A Collection of Deep Learning-based
Feature-Free Approaches for Characterizing Single-Objective Continuous Fitness
Landscapes. In: Proceedings of the Genetic and Evolutionary Computation Conference.
Association for Computing Machinery; 2022:657–665. doi:10.1145/3512290.3528834'
apa: Seiler, M., Prager, R. P., Kerschke, P., & Trautmann, H. (2022). A Collection
of Deep Learning-based Feature-Free Approaches for Characterizing Single-Objective
Continuous Fitness Landscapes. Proceedings of the Genetic and Evolutionary
Computation Conference, 657–665. https://doi.org/10.1145/3512290.3528834
bibtex: '@inproceedings{Seiler_Prager_Kerschke_Trautmann_2022, place={New York,
NY, USA}, title={A Collection of Deep Learning-based Feature-Free Approaches for
Characterizing Single-Objective Continuous Fitness Landscapes}, DOI={10.1145/3512290.3528834},
booktitle={Proceedings of the Genetic and Evolutionary Computation Conference},
publisher={Association for Computing Machinery}, author={Seiler, Moritz and Prager,
Raphael Patrick and Kerschke, Pascal and Trautmann, Heike}, year={2022}, pages={657–665}
}'
chicago: 'Seiler, Moritz, Raphael Patrick Prager, Pascal Kerschke, and Heike Trautmann.
“A Collection of Deep Learning-Based Feature-Free Approaches for Characterizing
Single-Objective Continuous Fitness Landscapes.” In Proceedings of the Genetic
and Evolutionary Computation Conference, 657–665. New York, NY, USA: Association
for Computing Machinery, 2022. https://doi.org/10.1145/3512290.3528834.'
ieee: 'M. Seiler, R. P. Prager, P. Kerschke, and H. Trautmann, “A Collection of
Deep Learning-based Feature-Free Approaches for Characterizing Single-Objective
Continuous Fitness Landscapes,” in Proceedings of the Genetic and Evolutionary
Computation Conference, 2022, pp. 657–665, doi: 10.1145/3512290.3528834.'
mla: Seiler, Moritz, et al. “A Collection of Deep Learning-Based Feature-Free Approaches
for Characterizing Single-Objective Continuous Fitness Landscapes.” Proceedings
of the Genetic and Evolutionary Computation Conference, Association for Computing
Machinery, 2022, pp. 657–665, doi:10.1145/3512290.3528834.
short: 'M. Seiler, R.P. Prager, P. Kerschke, H. Trautmann, in: Proceedings of the
Genetic and Evolutionary Computation Conference, Association for Computing Machinery,
New York, NY, USA, 2022, pp. 657–665.'
date_created: 2023-08-04T07:15:59Z
date_updated: 2024-06-07T07:13:23Z
department:
- _id: '34'
- _id: '819'
doi: 10.1145/3512290.3528834
language:
- iso: eng
page: 657–665
place: New York, NY, USA
publication: Proceedings of the Genetic and Evolutionary Computation Conference
publication_identifier:
isbn:
- '9781450392372'
publisher: Association for Computing Machinery
status: public
title: A Collection of Deep Learning-based Feature-Free Approaches for Characterizing
Single-Objective Continuous Fitness Landscapes
type: conference
user_id: '15504'
year: '2022'
...
---
_id: '46304'
abstract:
- lang: eng
text: In recent years, feature-based automated algorithm selection using exploratory
landscape analysis has demonstrated its great potential in single-objective continuous
black-box optimization. However, feature computation is problem-specific and can
be costly in terms of computational resources. This paper investigates feature-free
approaches that rely on state-of-the-art deep learning techniques operating on
either images or point clouds. We show that point-cloud-based strategies, in particular,
are highly competitive and also substantially reduce the size of the required
solver portfolio. Moreover, we highlight the effect and importance of cost-sensitive
learning in automated algorithm selection models.
author:
- first_name: Raphael Patrick
full_name: Prager, Raphael Patrick
last_name: Prager
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
citation:
ama: 'Prager RP, Seiler M, Trautmann H, Kerschke P. Automated Algorithm Selection
in Single-Objective Continuous Optimization: A Comparative Study of Deep Learning
and Landscape Analysis Methods. In: Rudolph G, Kononova AV, Aguirre H, Kerschke
P, Ochoa G, Tušar T, eds. Parallel Problem Solving from Nature — PPSN XVII.
Springer International Publishing; 2022:3–17. doi:10.1007/978-3-031-14714-2_1'
apa: 'Prager, R. P., Seiler, M., Trautmann, H., & Kerschke, P. (2022). Automated
Algorithm Selection in Single-Objective Continuous Optimization: A Comparative
Study of Deep Learning and Landscape Analysis Methods. In G. Rudolph, A. V. Kononova,
H. Aguirre, P. Kerschke, G. Ochoa, & T. Tušar (Eds.), Parallel Problem
Solving from Nature — PPSN XVII (pp. 3–17). Springer International Publishing.
https://doi.org/10.1007/978-3-031-14714-2_1'
bibtex: '@inproceedings{Prager_Seiler_Trautmann_Kerschke_2022, place={Cham}, title={Automated
Algorithm Selection in Single-Objective Continuous Optimization: A Comparative
Study of Deep Learning and Landscape Analysis Methods}, DOI={10.1007/978-3-031-14714-2_1},
booktitle={Parallel Problem Solving from Nature — PPSN XVII}, publisher={Springer
International Publishing}, author={Prager, Raphael Patrick and Seiler, Moritz
and Trautmann, Heike and Kerschke, Pascal}, editor={Rudolph, Günter and Kononova,
Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tušar,
Tea}, year={2022}, pages={3–17} }'
chicago: 'Prager, Raphael Patrick, Moritz Seiler, Heike Trautmann, and Pascal Kerschke.
“Automated Algorithm Selection in Single-Objective Continuous Optimization: A
Comparative Study of Deep Learning and Landscape Analysis Methods.” In Parallel
Problem Solving from Nature — PPSN XVII, edited by Günter Rudolph, Anna V.
Kononova, Hernán Aguirre, Pascal Kerschke, Gabriela Ochoa, and Tea Tušar, 3–17.
Cham: Springer International Publishing, 2022. https://doi.org/10.1007/978-3-031-14714-2_1.'
ieee: 'R. P. Prager, M. Seiler, H. Trautmann, and P. Kerschke, “Automated Algorithm
Selection in Single-Objective Continuous Optimization: A Comparative Study of
Deep Learning and Landscape Analysis Methods,” in Parallel Problem Solving
from Nature — PPSN XVII, 2022, pp. 3–17, doi: 10.1007/978-3-031-14714-2_1.'
mla: 'Prager, Raphael Patrick, et al. “Automated Algorithm Selection in Single-Objective
Continuous Optimization: A Comparative Study of Deep Learning and Landscape Analysis
Methods.” Parallel Problem Solving from Nature — PPSN XVII, edited by Günter
Rudolph et al., Springer International Publishing, 2022, pp. 3–17, doi:10.1007/978-3-031-14714-2_1.'
short: 'R.P. Prager, M. Seiler, H. Trautmann, P. Kerschke, in: G. Rudolph, A.V.
Kononova, H. Aguirre, P. Kerschke, G. Ochoa, T. Tušar (Eds.), Parallel Problem
Solving from Nature — PPSN XVII, Springer International Publishing, Cham, 2022,
pp. 3–17.'
date_created: 2023-08-04T07:12:33Z
date_updated: 2024-06-07T07:13:47Z
department:
- _id: '34'
- _id: '819'
doi: 10.1007/978-3-031-14714-2_1
editor:
- first_name: Günter
full_name: Rudolph, Günter
last_name: Rudolph
- first_name: Anna V.
full_name: Kononova, Anna V.
last_name: Kononova
- first_name: Hernán
full_name: Aguirre, Hernán
last_name: Aguirre
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
- first_name: Gabriela
full_name: Ochoa, Gabriela
last_name: Ochoa
- first_name: Tea
full_name: Tušar, Tea
last_name: Tušar
language:
- iso: eng
page: 3–17
place: Cham
publication: Parallel Problem Solving from Nature — PPSN XVII
publication_identifier:
isbn:
- 978-3-031-14714-2
publisher: Springer International Publishing
status: public
title: 'Automated Algorithm Selection in Single-Objective Continuous Optimization:
A Comparative Study of Deep Learning and Landscape Analysis Methods'
type: conference
user_id: '15504'
year: '2022'
...
---
_id: '46303'
abstract:
- lang: eng
text: Social media platforms are essential for information sharing and, thus, prone
to coordinated dis- and misinformation campaigns. Nevertheless, research in this
area is hampered by strict data sharing regulations imposed by the platforms,
resulting in a lack of benchmark data. Previous work focused on circumventing
these rules by either pseudonymizing the data or sharing fragments. In this work,
we will address the benchmarking crisis by presenting a methodology that can be
used to create artificial campaigns out of original campaign building blocks.
We conduct a proof-of-concept study using the freely available generative language
model GPT-Neo in this context and demonstrate that the campaign patterns can flexibly
be adapted to an underlying social media stream and evade state-of-the-art campaign
detection approaches based on stream clustering. Thus, we not only provide a framework
for artificial benchmark generation but also demonstrate the possible adversarial
nature of such benchmarks for challenging and advancing current campaign detection
methods.
author:
- first_name: Janina Susanne
full_name: Pohl, Janina Susanne
last_name: Pohl
- first_name: Dennis
full_name: Assenmacher, Dennis
last_name: Assenmacher
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Christian
full_name: Grimme, Christian
last_name: Grimme
citation:
ama: 'Pohl JS, Assenmacher D, Seiler M, Trautmann H, Grimme C. Artificial Social
Media Campaign Creation for Benchmarking and Challenging Detection Approaches.
In: the Advancement of Artificial Intelligence (AAAI) Association for, ed. Workshop
Proceedings of the 16$^th$ International Conference on Web and Social Media (ICWSM).
AAAI Press; 2022:1–10. doi:10.36190/2022.91'
apa: Pohl, J. S., Assenmacher, D., Seiler, M., Trautmann, H., & Grimme, C. (2022).
Artificial Social Media Campaign Creation for Benchmarking and Challenging Detection
Approaches. In for the Advancement of Artificial Intelligence (AAAI) Association
(Ed.), Workshop Proceedings of the 16$^th$ International Conference on Web
and Social Media (ICWSM) (pp. 1–10). AAAI Press. https://doi.org/10.36190/2022.91
bibtex: '@inproceedings{Pohl_Assenmacher_Seiler_Trautmann_Grimme_2022, place={Palo
Alto, CA, USA}, title={Artificial Social Media Campaign Creation for Benchmarking
and Challenging Detection Approaches}, DOI={10.36190/2022.91},
booktitle={Workshop Proceedings of the 16$^th$ International Conference on Web
and Social Media (ICWSM)}, publisher={AAAI Press}, author={Pohl, Janina Susanne
and Assenmacher, Dennis and Seiler, Moritz and Trautmann, Heike and Grimme, Christian},
editor={the Advancement of Artificial Intelligence (AAAI) Association, for}, year={2022},
pages={1–10} }'
chicago: 'Pohl, Janina Susanne, Dennis Assenmacher, Moritz Seiler, Heike Trautmann,
and Christian Grimme. “Artificial Social Media Campaign Creation for Benchmarking
and Challenging Detection Approaches.” In Workshop Proceedings of the 16$^th$
International Conference on Web and Social Media (ICWSM), edited by for the
Advancement of Artificial Intelligence (AAAI) Association, 1–10. Palo Alto, CA,
USA: AAAI Press, 2022. https://doi.org/10.36190/2022.91.'
ieee: 'J. S. Pohl, D. Assenmacher, M. Seiler, H. Trautmann, and C. Grimme, “Artificial
Social Media Campaign Creation for Benchmarking and Challenging Detection Approaches,”
in Workshop Proceedings of the 16$^th$ International Conference on Web and
Social Media (ICWSM), 2022, pp. 1–10, doi: 10.36190/2022.91.'
mla: Pohl, Janina Susanne, et al. “Artificial Social Media Campaign Creation for
Benchmarking and Challenging Detection Approaches.” Workshop Proceedings of
the 16$^th$ International Conference on Web and Social Media (ICWSM), edited
by for the Advancement of Artificial Intelligence (AAAI) Association, AAAI Press,
2022, pp. 1–10, doi:10.36190/2022.91.
short: 'J.S. Pohl, D. Assenmacher, M. Seiler, H. Trautmann, C. Grimme, in: for
the Advancement of Artificial Intelligence (AAAI) Association (Ed.), Workshop
Proceedings of the 16$^th$ International Conference on Web and Social Media (ICWSM),
AAAI Press, Palo Alto, CA, USA, 2022, pp. 1–10.'
date_created: 2023-08-04T07:11:34Z
date_updated: 2024-06-07T07:13:35Z
department:
- _id: '34'
- _id: '819'
doi: 10.36190/2022.91
editor:
- first_name: for
full_name: the Advancement of Artificial Intelligence (AAAI) Association, for
last_name: the Advancement of Artificial Intelligence (AAAI) Association
language:
- iso: eng
page: 1–10
place: Palo Alto, CA, USA
publication: Workshop Proceedings of the 16$^th$ International Conference on Web and
Social Media (ICWSM)
publisher: AAAI Press
status: public
title: Artificial Social Media Campaign Creation for Benchmarking and Challenging
Detection Approaches
type: conference
user_id: '15504'
year: '2022'
...
---
_id: '46315'
abstract:
- lang: eng
text: We propose a novel method for automated algorithm selection in the domain
of single-objective continuous black-box optimization. In contrast to existing
methods, we use convolutional neural networks as the selection apparatus which
bases its decision on a so-called ‘fitness map’. This fitness map is a 2D representation
of a two dimensional search space where different gray scales indicate the quality
of found solutions in certain areas. Our devised approach uses a modular CMA-ES
framework which offers the option to create the conventional CMA-ES, CMA-ES with
the alternate step-size adaptation and many other variants proposed over the years.
In total, 4 608 different configurations are possible where most configurations
are of complementary nature. In this proof-of-concept work, we consider a subset
of 32 possible configurations. The developed method is evaluated against an excerpt
of BBOB functions and its performance is compared against baselines that are commonly
used in automated algorithm selection - the best standalone algorithm (configuration)
and the best obtainable sequence of configurations. While the results indicate
that the use of the fitness map is not superior on every benchmark problem, it
indubitably shows its merit on more hard-to-solve problems. This offers a promising
perspective for generalizing to other types of optimization problems and problem
domains.
author:
- first_name: Raphael Patrick
full_name: Prager, Raphael Patrick
last_name: Prager
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
citation:
ama: 'Prager RP, Seiler M, Trautmann H, Kerschke P. Towards Feature-Free Automated
Algorithm Selection for Single-Objective Continuous Black-Box Optimization. In:
2021 IEEE Symposium Series on Computational Intelligence (SSCI). ; 2021:1-8.
doi:10.1109/SSCI50451.2021.9660174'
apa: Prager, R. P., Seiler, M., Trautmann, H., & Kerschke, P. (2021). Towards
Feature-Free Automated Algorithm Selection for Single-Objective Continuous Black-Box
Optimization. 2021 IEEE Symposium Series on Computational Intelligence (SSCI),
1–8. https://doi.org/10.1109/SSCI50451.2021.9660174
bibtex: '@inproceedings{Prager_Seiler_Trautmann_Kerschke_2021, title={Towards Feature-Free
Automated Algorithm Selection for Single-Objective Continuous Black-Box Optimization},
DOI={10.1109/SSCI50451.2021.9660174},
booktitle={2021 IEEE Symposium Series on Computational Intelligence (SSCI)}, author={Prager,
Raphael Patrick and Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal},
year={2021}, pages={1–8} }'
chicago: Prager, Raphael Patrick, Moritz Seiler, Heike Trautmann, and Pascal Kerschke.
“Towards Feature-Free Automated Algorithm Selection for Single-Objective Continuous
Black-Box Optimization.” In 2021 IEEE Symposium Series on Computational Intelligence
(SSCI), 1–8, 2021. https://doi.org/10.1109/SSCI50451.2021.9660174.
ieee: 'R. P. Prager, M. Seiler, H. Trautmann, and P. Kerschke, “Towards Feature-Free
Automated Algorithm Selection for Single-Objective Continuous Black-Box Optimization,”
in 2021 IEEE Symposium Series on Computational Intelligence (SSCI), 2021,
pp. 1–8, doi: 10.1109/SSCI50451.2021.9660174.'
mla: Prager, Raphael Patrick, et al. “Towards Feature-Free Automated Algorithm Selection
for Single-Objective Continuous Black-Box Optimization.” 2021 IEEE Symposium
Series on Computational Intelligence (SSCI), 2021, pp. 1–8, doi:10.1109/SSCI50451.2021.9660174.
short: 'R.P. Prager, M. Seiler, H. Trautmann, P. Kerschke, in: 2021 IEEE Symposium
Series on Computational Intelligence (SSCI), 2021, pp. 1–8.'
date_created: 2023-08-04T07:25:08Z
date_updated: 2024-06-07T07:12:28Z
department:
- _id: '34'
- _id: '819'
doi: 10.1109/SSCI50451.2021.9660174
language:
- iso: eng
page: 1-8
publication: 2021 IEEE Symposium Series on Computational Intelligence (SSCI)
status: public
title: Towards Feature-Free Automated Algorithm Selection for Single-Objective Continuous
Black-Box Optimization
type: conference
user_id: '15504'
year: '2021'
...
---
_id: '46312'
abstract:
- lang: eng
text: Abuse and hate are penetrating social media and many comment sections of news
media companies. These platform providers invest considerable efforts to mod-
erate user-generated contributions to prevent losing readers who get appalled
by inappropriate texts. This is further enforced by legislative actions, which
make non-clearance of these comments a punishable action. While (semi-)automated
solutions using Natural Language Processing and advanced Machine Learning techniques
are getting increasingly sophisticated, the domain of abusive language detection
still struggles as large non-English and well-curated datasets are scarce or not
publicly available. With this work, we publish and analyse the largest annotated
German abusive language comment datasets to date. In contrast to existing datasets,
we achieve a high labelling standard by conducting a thorough crowd-based an-
notation study that complements professional moderators’ decisions, which are
also included in the dataset. We compare and cross-evaluate the performance of
baseline algorithms and state-of-the-art transformer-based language models, which
are fine-tuned on our datasets and an existing alternative, showing the usefulness
for the community.
author:
- first_name: Dennis
full_name: Assenmacher, Dennis
last_name: Assenmacher
- first_name: Marco
full_name: Niemann, Marco
last_name: Niemann
- first_name: Kilian
full_name: Müller, Kilian
last_name: Müller
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Dennis M.
full_name: Riehle, Dennis M.
last_name: Riehle
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Assenmacher D, Niemann M, Müller K, Seiler M, Riehle DM, Trautmann H. RP-Mod
& RP-Crowd: Moderator- and Crowd-Annotated German News Comment Datasets. In:
Proceedings of the Neural Information Processing Systems Track on Datasets
and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021). ; 2021:1–14.'
apa: 'Assenmacher, D., Niemann, M., Müller, K., Seiler, M., Riehle, D. M., &
Trautmann, H. (2021). RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated German
News Comment Datasets. Proceedings of the Neural Information Processing Systems
Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021),
1–14.'
bibtex: '@inproceedings{Assenmacher_Niemann_Müller_Seiler_Riehle_Trautmann_2021,
place={Virtual Event}, title={RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated
German News Comment Datasets}, booktitle={Proceedings of the Neural Information
Processing Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks
2021)}, author={Assenmacher, Dennis and Niemann, Marco and Müller, Kilian and
Seiler, Moritz and Riehle, Dennis M. and Trautmann, Heike}, year={2021}, pages={1–14}
}'
chicago: 'Assenmacher, Dennis, Marco Niemann, Kilian Müller, Moritz Seiler, Dennis
M. Riehle, and Heike Trautmann. “RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated
German News Comment Datasets.” In Proceedings of the Neural Information Processing
Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021),
1–14. Virtual Event, 2021.'
ieee: 'D. Assenmacher, M. Niemann, K. Müller, M. Seiler, D. M. Riehle, and H. Trautmann,
“RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated German News Comment Datasets,”
in Proceedings of the Neural Information Processing Systems Track on Datasets
and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021), 2021, pp. 1–14.'
mla: 'Assenmacher, Dennis, et al. “RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated
German News Comment Datasets.” Proceedings of the Neural Information Processing
Systems Track on Datasets and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021),
2021, pp. 1–14.'
short: 'D. Assenmacher, M. Niemann, K. Müller, M. Seiler, D.M. Riehle, H. Trautmann,
in: Proceedings of the Neural Information Processing Systems Track on Datasets
and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021), Virtual Event, 2021,
pp. 1–14.'
date_created: 2023-08-04T07:22:59Z
date_updated: 2024-06-07T07:13:04Z
department:
- _id: '34'
- _id: '819'
language:
- iso: eng
page: 1–14
place: Virtual Event
publication: Proceedings of the Neural Information Processing Systems Track on Datasets
and Benchmarks 1 (NeurIPS Datasets and Benchmarks 2021)
status: public
title: 'RP-Mod & RP-Crowd: Moderator- and Crowd-Annotated German News Comment Datasets'
type: conference
user_id: '15504'
year: '2021'
...
---
_id: '46313'
abstract:
- lang: eng
text: 'Classic automated algorithm selection (AS) for (combinatorial) optimization
problems heavily relies on so-called instance features, i.e., numerical characteristics
of the problem at hand ideally extracted with computationally low-demanding routines.
For the traveling salesperson problem (TSP) a plethora of features have been suggested.
Most of these features are, if at all, only normalized imprecisely raising the
issue of feature values being strongly affected by the instance size. Such artifacts
may have detrimental effects on algorithm selection models. We propose a normalization
for two feature groups which stood out in multiple AS studies on the TSP: (a)
features based on a minimum spanning tree (MST) and (b) a k-nearest neighbor graph
(NNG) transformation of the input instance. To this end we theoretically derive
minimum and maximum values for properties of MSTs and k-NNGs of Euclidean graphs.
We analyze the differences in feature space between normalized versions of these
features and their unnormalized counterparts. Our empirical investigations on
various TSP benchmark sets point out that the feature scaling succeeds in eliminating
the effect of the instance size. Eventually, a proof-of-concept AS-study shows
promising results: models trained with normalized features tend to outperform
those trained with the respective vanilla features.'
author:
- first_name: Jonathan
full_name: Heins, Jonathan
last_name: Heins
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Janina
full_name: Pohl, Janina
last_name: Pohl
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
citation:
ama: 'Heins J, Bossek J, Pohl J, Seiler M, Trautmann H, Kerschke P. On the Potential
of Normalized TSP Features for Automated Algorithm Selection. In: Computing Machinery
Association for, ed. Proceedings of the 16$^th$ ACM/SIGEVO Conference on Foundations
of Genetic Algorithms (FOGA XVI). Association for Computing Machinery; 2021:1–15.
doi:10.1145/3450218.3477308'
apa: Heins, J., Bossek, J., Pohl, J., Seiler, M., Trautmann, H., & Kerschke,
P. (2021). On the Potential of Normalized TSP Features for Automated Algorithm
Selection. In for Computing Machinery Association (Ed.), Proceedings of the
16$^th$ ACM/SIGEVO Conference on Foundations of genetic Algorithms (FOGA XVI)
(pp. 1–15). Association for Computing Machinery. https://doi.org/10.1145/3450218.3477308
bibtex: '@inproceedings{Heins_Bossek_Pohl_Seiler_Trautmann_Kerschke_2021, place={Dornbirn,
Austria}, title={On the Potential of Normalized TSP Features for Automated Algorithm
Selection}, DOI={10.1145/3450218.3477308},
booktitle={Proceedings of the 16$^th$ ACM/SIGEVO Conference on Foundations of
genetic Algorithms (FOGA XVI)}, publisher={Association for Computing Machinery},
author={Heins, Jonathan and Bossek, Jakob and Pohl, Janina and Seiler, Moritz
and Trautmann, Heike and Kerschke, Pascal}, editor={Computing Machinery Association,
for}, year={2021}, pages={1–15} }'
chicago: 'Heins, Jonathan, Jakob Bossek, Janina Pohl, Moritz Seiler, Heike Trautmann,
and Pascal Kerschke. “On the Potential of Normalized TSP Features for Automated
Algorithm Selection.” In Proceedings of the 16$^th$ ACM/SIGEVO Conference on
Foundations of Genetic Algorithms (FOGA XVI), edited by for Computing Machinery
Association, 1–15. Dornbirn, Austria: Association for Computing Machinery, 2021.
https://doi.org/10.1145/3450218.3477308.'
ieee: 'J. Heins, J. Bossek, J. Pohl, M. Seiler, H. Trautmann, and P. Kerschke, “On
the Potential of Normalized TSP Features for Automated Algorithm Selection,” in
Proceedings of the 16$^th$ ACM/SIGEVO Conference on Foundations of genetic
Algorithms (FOGA XVI), 2021, pp. 1–15, doi: 10.1145/3450218.3477308.'
mla: Heins, Jonathan, et al. “On the Potential of Normalized TSP Features for Automated
Algorithm Selection.” Proceedings of the 16$^th$ ACM/SIGEVO Conference on Foundations
of Genetic Algorithms (FOGA XVI), edited by for Computing Machinery Association,
Association for Computing Machinery, 2021, pp. 1–15, doi:10.1145/3450218.3477308.
short: 'J. Heins, J. Bossek, J. Pohl, M. Seiler, H. Trautmann, P. Kerschke, in: for
Computing Machinery Association (Ed.), Proceedings of the 16$^th$ ACM/SIGEVO Conference
on Foundations of Genetic Algorithms (FOGA XVI), Association for Computing Machinery,
Dornbirn, Austria, 2021, pp. 1–15.'
date_created: 2023-08-04T07:23:57Z
date_updated: 2024-06-10T11:57:04Z
department:
- _id: '34'
- _id: '819'
doi: 10.1145/3450218.3477308
editor:
- first_name: for
full_name: Computing Machinery Association, for
last_name: Computing Machinery Association
language:
- iso: eng
page: 1–15
place: Dornbirn, Austria
publication: Proceedings of the 16$^th$ ACM/SIGEVO Conference on Foundations of genetic
Algorithms (FOGA XVI)
publisher: Association for Computing Machinery
status: public
title: On the Potential of Normalized TSP Features for Automated Algorithm Selection
type: conference
user_id: '15504'
year: '2021'
...
---
_id: '46331'
abstract:
- lang: eng
text: Artificial neural networks in general and deep learning networks in particular
established themselves as popular and powerful machine learning algorithms. While
the often tremendous sizes of these networks are beneficial when solving complex
tasks, the tremendous number of parameters also causes such networks to be vulnerable
to malicious behavior such as adversarial perturbations. These perturbations can
change a model's classification decision. Moreover, while single-step adversaries
can easily be transferred from network to network, the transfer of more powerful
multi-step adversaries has - usually - been rather difficult.In this work, we
introduce a method for generating strong adversaries that can easily (and frequently)
be transferred between different models. This method is then used to generate
a large set of adversaries, based on which the effects of selected defense methods
are experimentally assessed. At last, we introduce a novel, simple, yet effective
approach to enhance the resilience of neural networks against adversaries and
benchmark it against established defense methods. In contrast to the already existing
methods, our proposed defense approach is much more efficient as it only requires
a single additional forward-pass to achieve comparable performance results.
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
citation:
ama: 'Seiler M, Trautmann H, Kerschke P. Enhancing Resilience of Deep Learning Networks
By Means of Transferable Adversaries. In: Proceedings of the International
Joint Conference on Neural Networks (IJCNN). ; 2020:1–8. doi:10.1109/IJCNN48605.2020.9207338'
apa: Seiler, M., Trautmann, H., & Kerschke, P. (2020). Enhancing Resilience
of Deep Learning Networks By Means of Transferable Adversaries. Proceedings
of the International Joint Conference on Neural Networks (IJCNN), 1–8. https://doi.org/10.1109/IJCNN48605.2020.9207338
bibtex: '@inproceedings{Seiler_Trautmann_Kerschke_2020, place={Glasgow, UK}, title={Enhancing
Resilience of Deep Learning Networks By Means of Transferable Adversaries}, DOI={10.1109/IJCNN48605.2020.9207338},
booktitle={Proceedings of the International Joint Conference on Neural Networks
(IJCNN)}, author={Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal}, year={2020},
pages={1–8} }'
chicago: Seiler, Moritz, Heike Trautmann, and Pascal Kerschke. “Enhancing Resilience
of Deep Learning Networks By Means of Transferable Adversaries.” In Proceedings
of the International Joint Conference on Neural Networks (IJCNN), 1–8. Glasgow,
UK, 2020. https://doi.org/10.1109/IJCNN48605.2020.9207338.
ieee: 'M. Seiler, H. Trautmann, and P. Kerschke, “Enhancing Resilience of Deep Learning
Networks By Means of Transferable Adversaries,” in Proceedings of the International
Joint Conference on Neural Networks (IJCNN), 2020, pp. 1–8, doi: 10.1109/IJCNN48605.2020.9207338.'
mla: Seiler, Moritz, et al. “Enhancing Resilience of Deep Learning Networks By Means
of Transferable Adversaries.” Proceedings of the International Joint Conference
on Neural Networks (IJCNN), 2020, pp. 1–8, doi:10.1109/IJCNN48605.2020.9207338.
short: 'M. Seiler, H. Trautmann, P. Kerschke, in: Proceedings of the International
Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020, pp. 1–8.'
date_created: 2023-08-04T07:39:48Z
date_updated: 2024-06-07T07:11:53Z
department:
- _id: '34'
- _id: '819'
doi: 10.1109/IJCNN48605.2020.9207338
language:
- iso: eng
page: 1–8
place: Glasgow, UK
publication: Proceedings of the International Joint Conference on Neural Networks
(IJCNN)
status: public
title: Enhancing Resilience of Deep Learning Networks By Means of Transferable Adversaries
type: conference
user_id: '15504'
year: '2020'
...
---
_id: '46330'
abstract:
- lang: eng
text: 'In this work we focus on the well-known Euclidean Traveling Salesperson Problem
(TSP) and two highly competitive inexact heuristic TSP solvers, EAX and LKH, in
the context of per-instance algorithm selection (AS). We evolve instances with
1000 nodes where the solvers show strongly different performance profiles. These
instances serve as a basis for an exploratory study on the identification of well-discriminating
problem characteristics (features). Our results in a nutshell: we show that even
though (1) promising features exist, (2) these are in line with previous results
from the literature, and (3) models trained with these features are more accurate
than models adopting sophisticated feature selection methods, the advantage is
not close to the virtual best solver in terms of penalized average runtime and
so is the performance gain over the single best solver. However, we show that
a feature-free deep neural network based approach solely based on visual representation
of the instances already matches classical AS model results and thus shows huge
potential for future studies.'
author:
- first_name: Moritz
full_name: Seiler, Moritz
id: '105520'
last_name: Seiler
- first_name: Janina
full_name: Pohl, Janina
last_name: Pohl
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Pascal
full_name: Kerschke, Pascal
last_name: Kerschke
- first_name: Heike
full_name: Trautmann, Heike
id: '100740'
last_name: Trautmann
orcid: 0000-0002-9788-8282
citation:
ama: 'Seiler M, Pohl J, Bossek J, Kerschke P, Trautmann H. Deep Learning as a Competitive
Feature-Free Approach for Automated Algorithm Selection on the Traveling Salesperson
Problem. In: Bäck T, Preuss M, Deutz A, et al., eds. Proceedings of the 16$^th$
International Conference on Parallel Problem Solving from Nature (PPSN XVI).
; 2020:48–64. doi:10.1007/978-3-030-58112-1_4'
apa: Seiler, M., Pohl, J., Bossek, J., Kerschke, P., & Trautmann, H. (2020).
Deep Learning as a Competitive Feature-Free Approach for Automated Algorithm Selection
on the Traveling Salesperson Problem. In T. Bäck, M. Preuss, A. Deutz, H. Wang,
C. Doerr, M. Emmerich, & H. Trautmann (Eds.), Proceedings of the 16$^th$
International Conference on Parallel Problem Solving from Nature (PPSN XVI)
(pp. 48–64). https://doi.org/10.1007/978-3-030-58112-1_4
bibtex: '@inproceedings{Seiler_Pohl_Bossek_Kerschke_Trautmann_2020, place={Leiden,
The Netherlands}, title={Deep Learning as a Competitive Feature-Free Approach
for Automated Algorithm Selection on the Traveling Salesperson Problem}, DOI={10.1007/978-3-030-58112-1_4},
booktitle={Proceedings of the 16$^th$ International Conference on Parallel Problem
Solving from Nature (PPSN XVI)}, author={Seiler, Moritz and Pohl, Janina and Bossek,
Jakob and Kerschke, Pascal and Trautmann, Heike}, editor={Bäck, Thomas and Preuss,
Mike and Deutz, André and Wang, Hao and Doerr, Carola and Emmerich, Michael and
Trautmann, Heike}, year={2020}, pages={48–64} }'
chicago: Seiler, Moritz, Janina Pohl, Jakob Bossek, Pascal Kerschke, and Heike Trautmann.
“Deep Learning as a Competitive Feature-Free Approach for Automated Algorithm
Selection on the Traveling Salesperson Problem.” In Proceedings of the 16$^th$
International Conference on Parallel Problem Solving from Nature (PPSN XVI),
edited by Thomas Bäck, Mike Preuss, André Deutz, Hao Wang, Carola Doerr, Michael
Emmerich, and Heike Trautmann, 48–64. Leiden, The Netherlands, 2020. https://doi.org/10.1007/978-3-030-58112-1_4.
ieee: 'M. Seiler, J. Pohl, J. Bossek, P. Kerschke, and H. Trautmann, “Deep Learning
as a Competitive Feature-Free Approach for Automated Algorithm Selection on the
Traveling Salesperson Problem,” in Proceedings of the 16$^th$ International
Conference on Parallel Problem Solving from Nature (PPSN XVI), 2020, pp. 48–64,
doi: 10.1007/978-3-030-58112-1_4.'
mla: Seiler, Moritz, et al. “Deep Learning as a Competitive Feature-Free Approach
for Automated Algorithm Selection on the Traveling Salesperson Problem.” Proceedings
of the 16$^th$ International Conference on Parallel Problem Solving from Nature
(PPSN XVI), edited by Thomas Bäck et al., 2020, pp. 48–64, doi:10.1007/978-3-030-58112-1_4.
short: 'M. Seiler, J. Pohl, J. Bossek, P. Kerschke, H. Trautmann, in: T. Bäck, M.
Preuss, A. Deutz, H. Wang, C. Doerr, M. Emmerich, H. Trautmann (Eds.), Proceedings
of the 16$^th$ International Conference on Parallel Problem Solving from Nature
(PPSN XVI), Leiden, The Netherlands, 2020, pp. 48–64.'
date_created: 2023-08-04T07:39:05Z
date_updated: 2024-06-10T11:57:13Z
department:
- _id: '34'
- _id: '819'
doi: 10.1007/978-3-030-58112-1_4
editor:
- first_name: Thomas
full_name: Bäck, Thomas
last_name: Bäck
- first_name: Mike
full_name: Preuss, Mike
last_name: Preuss
- first_name: André
full_name: Deutz, André
last_name: Deutz
- first_name: Hao
full_name: Wang, Hao
last_name: Wang
- first_name: Carola
full_name: Doerr, Carola
last_name: Doerr
- first_name: Michael
full_name: Emmerich, Michael
last_name: Emmerich
- first_name: Heike
full_name: Trautmann, Heike
last_name: Trautmann
language:
- iso: eng
page: 48–64
place: Leiden, The Netherlands
publication: Proceedings of the 16$^th$ International Conference on Parallel Problem
Solving from Nature (PPSN XVI)
status: public
title: Deep Learning as a Competitive Feature-Free Approach for Automated Algorithm
Selection on the Traveling Salesperson Problem
type: conference
user_id: '15504'
year: '2020'
...