---
_id: '67307'
author:
- first_name: Sedjro Salomon
full_name: Hotegni, Sedjro Salomon
id: '97995'
last_name: Hotegni
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: 'Hotegni SS, Peitz S. SPREAD: Sampling-based Pareto front Refinement via Efficient
Adaptive Diffusion. In: 14th International Conference on Learning Representations
(ICLR). ; 2026. doi:10.48550/arXiv.2509.21058'
apa: 'Hotegni, S. S., & Peitz, S. (2026). SPREAD: Sampling-based Pareto front
Refinement via Efficient Adaptive Diffusion. 14th International Conference
on Learning Representations (ICLR). https://doi.org/10.48550/arXiv.2509.21058'
bibtex: '@inproceedings{Hotegni_Peitz_2026, title={SPREAD: Sampling-based Pareto
front Refinement via Efficient Adaptive Diffusion}, DOI={10.48550/arXiv.2509.21058},
booktitle={14th International Conference on Learning Representations (ICLR)},
author={Hotegni, Sedjro Salomon and Peitz, Sebastian}, year={2026} }'
chicago: 'Hotegni, Sedjro Salomon, and Sebastian Peitz. “SPREAD: Sampling-Based
Pareto Front Refinement via Efficient Adaptive Diffusion.” In 14th International
Conference on Learning Representations (ICLR), 2026. https://doi.org/10.48550/arXiv.2509.21058.'
ieee: 'S. S. Hotegni and S. Peitz, “SPREAD: Sampling-based Pareto front Refinement
via Efficient Adaptive Diffusion,” 2026, doi: 10.48550/arXiv.2509.21058.'
mla: 'Hotegni, Sedjro Salomon, and Sebastian Peitz. “SPREAD: Sampling-Based Pareto
Front Refinement via Efficient Adaptive Diffusion.” 14th International Conference
on Learning Representations (ICLR), 2026, doi:10.48550/arXiv.2509.21058.'
short: 'S.S. Hotegni, S. Peitz, in: 14th International Conference on Learning Representations
(ICLR), 2026.'
date_created: 2026-10-01T12:01:30Z
date_updated: 2026-10-01T12:02:30Z
department:
- _id: '655'
doi: 10.48550/arXiv.2509.21058
keyword:
- own
- own-conference
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openreview.net/pdf?id=4731mIqv89
oa: '1'
publication: 14th International Conference on Learning Representations (ICLR)
status: public
title: 'SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion'
type: conference
user_id: '47427'
year: '2026'
...
---
_id: '67300'
abstract:
- lang: eng
text: Deep neural networks (DNNs) are vulnerable to small adversarial perturbations,
which are tiny changes to the input data that appear insignificant but cause the
model to produce drastically different outputs. Many defense methods require modifying
model architectures during evaluation or performing test-time data purification.
This not only introduces additional complexity but is often architecture-dependent.
We show, however, that robust feature learning during training can significantly
enhance DNN robustness. We propose MOREL, a multi-objective approach that aligns
natural and adversarial features using cosine similarity and multi-positive contrastive
losses to encourage similar features for same-class inputs. Extensive experiments
demonstrate that MOREL significantly improves robustness against both white-box
and black-box attacks. Our code is available at https://github.com/salomonhotegni/MOREL.
author:
- first_name: Sedjro Salomon
full_name: Hotegni, Sedjro Salomon
id: '97995'
last_name: Hotegni
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: 'Hotegni SS, Peitz S. Enhancing Adversarial Robustness Through Multi-objective
Representation Learning. In: Senn W, Sanguineti M, Saudargiene A, et al., eds.
Artificial Neural Networks and Machine Learning – ICANN 2025. Springer
Nature Switzerland; 2026:442–454. doi:10.1007/978-3-032-04558-4_35'
apa: Hotegni, S. S., & Peitz, S. (2026). Enhancing Adversarial Robustness Through
Multi-objective Representation Learning. In W. Senn, M. Sanguineti, A. Saudargiene,
I. V. Tetko, A. E. P. Villa, V. Jirsa, & Y. Bengio (Eds.), Artificial Neural
Networks and Machine Learning – ICANN 2025 (pp. 442–454). Springer Nature
Switzerland. https://doi.org/10.1007/978-3-032-04558-4_35
bibtex: '@inproceedings{Hotegni_Peitz_2026, place={Cham}, title={Enhancing Adversarial
Robustness Through Multi-objective Representation Learning}, DOI={10.1007/978-3-032-04558-4_35},
booktitle={Artificial Neural Networks and Machine Learning – ICANN 2025}, publisher={Springer
Nature Switzerland}, author={Hotegni, Sedjro Salomon and Peitz, Sebastian}, editor={Senn,
Walter and Sanguineti, Marcello and Saudargiene, Ausra and Tetko, Igor V. and
Villa, Alessandro E. P. and Jirsa, Viktor and Bengio, Yoshua}, year={2026}, pages={442–454}
}'
chicago: 'Hotegni, Sedjro Salomon, and Sebastian Peitz. “Enhancing Adversarial Robustness
Through Multi-Objective Representation Learning.” In Artificial Neural Networks
and Machine Learning – ICANN 2025, edited by Walter Senn, Marcello Sanguineti,
Ausra Saudargiene, Igor V. Tetko, Alessandro E. P. Villa, Viktor Jirsa, and Yoshua
Bengio, 442–454. Cham: Springer Nature Switzerland, 2026. https://doi.org/10.1007/978-3-032-04558-4_35.'
ieee: 'S. S. Hotegni and S. Peitz, “Enhancing Adversarial Robustness Through Multi-objective
Representation Learning,” in Artificial Neural Networks and Machine Learning
– ICANN 2025, 2026, pp. 442–454, doi: 10.1007/978-3-032-04558-4_35.'
mla: Hotegni, Sedjro Salomon, and Sebastian Peitz. “Enhancing Adversarial Robustness
Through Multi-Objective Representation Learning.” Artificial Neural Networks
and Machine Learning – ICANN 2025, edited by Walter Senn et al., Springer
Nature Switzerland, 2026, pp. 442–454, doi:10.1007/978-3-032-04558-4_35.
short: 'S.S. Hotegni, S. Peitz, in: W. Senn, M. Sanguineti, A. Saudargiene, I.V.
Tetko, A.E.P. Villa, V. Jirsa, Y. Bengio (Eds.), Artificial Neural Networks and
Machine Learning – ICANN 2025, Springer Nature Switzerland, Cham, 2026, pp. 442–454.'
date_created: 2026-10-01T11:53:11Z
date_updated: 2026-10-01T11:53:46Z
department:
- _id: '655'
doi: 10.1007/978-3-032-04558-4_35
editor:
- first_name: Walter
full_name: Senn, Walter
last_name: Senn
- first_name: Marcello
full_name: Sanguineti, Marcello
last_name: Sanguineti
- first_name: Ausra
full_name: Saudargiene, Ausra
last_name: Saudargiene
- first_name: Igor V.
full_name: Tetko, Igor V.
last_name: Tetko
- first_name: Alessandro E. P.
full_name: Villa, Alessandro E. P.
last_name: Villa
- first_name: Viktor
full_name: Jirsa, Viktor
last_name: Jirsa
- first_name: Yoshua
full_name: Bengio, Yoshua
last_name: Bengio
keyword:
- own
- own-conference
language:
- iso: eng
page: 442–454
place: Cham
publication: Artificial Neural Networks and Machine Learning – ICANN 2025
publication_identifier:
isbn:
- 978-3-032-04558-4
publisher: Springer Nature Switzerland
status: public
title: Enhancing Adversarial Robustness Through Multi-objective Representation Learning
type: conference
user_id: '47427'
year: '2026'
...
---
_id: '67316'
author:
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
- first_name: Sedjro Salomon
full_name: Hotegni, Sedjro Salomon
id: '97995'
last_name: Hotegni
citation:
ama: 'Peitz S, Hotegni SS. Multi-objective Deep Learning: Taxonomy and Survey of
the State of the Art. Machine Learning with Applications. 2025;(100700).
doi:10.1016/j.mlwa.2025.100700'
apa: 'Peitz, S., & Hotegni, S. S. (2025). Multi-objective Deep Learning: Taxonomy
and Survey of the State of the Art. Machine Learning with Applications,
100700. https://doi.org/10.1016/j.mlwa.2025.100700'
bibtex: '@article{Peitz_Hotegni_2025, title={Multi-objective Deep Learning: Taxonomy
and Survey of the State of the Art}, DOI={10.1016/j.mlwa.2025.100700},
number={100700}, journal={Machine Learning with Applications}, author={Peitz,
Sebastian and Hotegni, Sedjro Salomon}, year={2025} }'
chicago: 'Peitz, Sebastian, and Sedjro Salomon Hotegni. “Multi-Objective Deep Learning:
Taxonomy and Survey of the State of the Art.” Machine Learning with Applications,
no. 100700 (2025). https://doi.org/10.1016/j.mlwa.2025.100700.'
ieee: 'S. Peitz and S. S. Hotegni, “Multi-objective Deep Learning: Taxonomy and
Survey of the State of the Art,” Machine Learning with Applications, no.
100700, 2025, doi: 10.1016/j.mlwa.2025.100700.'
mla: 'Peitz, Sebastian, and Sedjro Salomon Hotegni. “Multi-Objective Deep Learning:
Taxonomy and Survey of the State of the Art.” Machine Learning with Applications,
no. 100700, 2025, doi:10.1016/j.mlwa.2025.100700.'
short: S. Peitz, S.S. Hotegni, Machine Learning with Applications (2025).
date_created: 2026-10-01T12:05:57Z
date_updated: 2026-10-01T12:06:04Z
department:
- _id: '655'
doi: 10.1016/j.mlwa.2025.100700
issue: '100700'
keyword:
- own
- own-journal
language:
- iso: eng
publication: Machine Learning with Applications
status: public
title: 'Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art'
type: journal_article
user_id: '47427'
year: '2025'
...
---
_id: '46649'
abstract:
- lang: eng
text: "Different conflicting optimization criteria arise naturally in various Deep\r\nLearning
scenarios. These can address different main tasks (i.e., in the\r\nsetting of
Multi-Task Learning), but also main and secondary tasks such as loss\r\nminimization
versus sparsity. The usual approach is a simple weighting of the\r\ncriteria,
which formally only works in the convex setting. In this paper, we\r\npresent
a Multi-Objective Optimization algorithm using a modified Weighted\r\nChebyshev
scalarization for training Deep Neural Networks (DNNs) with respect\r\nto several
tasks. By employing this scalarization technique, the algorithm can\r\nidentify
all optimal solutions of the original problem while reducing its\r\ncomplexity
to a sequence of single-objective problems. The simplified problems\r\nare then
solved using an Augmented Lagrangian method, enabling the use of\r\npopular optimization
techniques such as Adam and Stochastic Gradient Descent,\r\nwhile efficaciously
handling constraints. Our work aims to address the\r\n(economical and also ecological)
sustainability issue of DNN models, with a\r\nparticular focus on Deep Multi-Task
models, which are typically designed with a\r\nvery large number of weights to
perform equally well on multiple tasks. Through\r\nexperiments conducted on two
Machine Learning datasets, we demonstrate the\r\npossibility of adaptively sparsifying
the model during training without\r\nsignificantly impacting its performance,
if we are willing to apply\r\ntask-specific adaptations to the network weights.
Code is available at\r\nhttps://github.com/salomonhotegni/MDMTN."
author:
- first_name: Sedjro Salomon
full_name: Hotegni, Sedjro Salomon
id: '97995'
last_name: Hotegni
- first_name: Manuel Bastian
full_name: Berkemeier, Manuel Bastian
id: '51701'
last_name: Berkemeier
- first_name: Sebastian
full_name: Peitz, Sebastian
id: '47427'
last_name: Peitz
orcid: 0000-0002-3389-793X
citation:
ama: 'Hotegni SS, Berkemeier MB, Peitz S. Multi-Objective Optimization for Sparse
Deep Multi-Task Learning. In: 2024 International Joint Conference on Neural
Networks (IJCNN). IEEE; 2024:9. doi:10.1109/IJCNN60899.2024.10650994'
apa: Hotegni, S. S., Berkemeier, M. B., & Peitz, S. (2024). Multi-Objective
Optimization for Sparse Deep Multi-Task Learning. 2024 International Joint
Conference on Neural Networks (IJCNN), 9. https://doi.org/10.1109/IJCNN60899.2024.10650994
bibtex: '@inproceedings{Hotegni_Berkemeier_Peitz_2024, place={Yokohama, Japan},
title={Multi-Objective Optimization for Sparse Deep Multi-Task Learning}, DOI={10.1109/IJCNN60899.2024.10650994},
booktitle={2024 International Joint Conference on Neural Networks (IJCNN)}, publisher={IEEE},
author={Hotegni, Sedjro Salomon and Berkemeier, Manuel Bastian and Peitz, Sebastian},
year={2024}, pages={9} }'
chicago: 'Hotegni, Sedjro Salomon, Manuel Bastian Berkemeier, and Sebastian Peitz.
“Multi-Objective Optimization for Sparse Deep Multi-Task Learning.” In 2024
International Joint Conference on Neural Networks (IJCNN), 9. Yokohama, Japan:
IEEE, 2024. https://doi.org/10.1109/IJCNN60899.2024.10650994.'
ieee: 'S. S. Hotegni, M. B. Berkemeier, and S. Peitz, “Multi-Objective Optimization
for Sparse Deep Multi-Task Learning,” in 2024 International Joint Conference
on Neural Networks (IJCNN), Yokohama, Japan, 2024, p. 9, doi: 10.1109/IJCNN60899.2024.10650994.'
mla: Hotegni, Sedjro Salomon, et al. “Multi-Objective Optimization for Sparse Deep
Multi-Task Learning.” 2024 International Joint Conference on Neural Networks
(IJCNN), IEEE, 2024, p. 9, doi:10.1109/IJCNN60899.2024.10650994.
short: 'S.S. Hotegni, M.B. Berkemeier, S. Peitz, in: 2024 International Joint Conference
on Neural Networks (IJCNN), IEEE, Yokohama, Japan, 2024, p. 9.'
conference:
end_date: 2024-07-05
location: Yokohama, Japan
name: 2024 International Joint Conference on Neural Networks (IJCNN)
start_date: 2024-06-30
date_created: 2023-08-24T07:44:36Z
date_updated: 2024-09-27T10:24:22Z
department:
- _id: '655'
doi: 10.1109/IJCNN60899.2024.10650994
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://ieeexplore.ieee.org/document/10650994
oa: '1'
page: '9'
place: Yokohama, Japan
publication: 2024 International Joint Conference on Neural Networks (IJCNN)
publication_identifier:
eisbn:
- 979-8-3503-5931-2
eissn:
- ' 2161-4407'
publication_status: published
publisher: IEEE
status: public
title: Multi-Objective Optimization for Sparse Deep Multi-Task Learning
type: conference
user_id: '97995'
year: '2024'
...
---
_id: '45695'
author:
- first_name: Sedjro Salomon
full_name: Hotegni, Sedjro Salomon
id: '97995'
last_name: Hotegni
- first_name: Sepideh
full_name: Mahabadi, Sepideh
last_name: Mahabadi
- first_name: Ali
full_name: Vakilian, Ali
last_name: Vakilian
citation:
ama: 'Hotegni SS, Mahabadi S, Vakilian A. Approximation Algorithms for Fair Range
Clustering. In: Proceedings of the 40th International Conference on Machine
Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.'
apa: Hotegni, S. S., Mahabadi, S., & Vakilian, A. (n.d.). Approximation Algorithms
for Fair Range Clustering. Proceedings of the 40th International Conference
on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023. International
Conference on Machine Learning, Honolulu, Hawaii, USA.
bibtex: '@inproceedings{Hotegni_Mahabadi_Vakilian, title={Approximation Algorithms
for Fair Range Clustering}, booktitle={Proceedings of the 40th International Conference
on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.}, author={Hotegni,
Sedjro Salomon and Mahabadi, Sepideh and Vakilian, Ali} }'
chicago: Hotegni, Sedjro Salomon, Sepideh Mahabadi, and Ali Vakilian. “Approximation
Algorithms for Fair Range Clustering.” In Proceedings of the 40th International
Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023., n.d.
ieee: S. S. Hotegni, S. Mahabadi, and A. Vakilian, “Approximation Algorithms for
Fair Range Clustering,” presented at the International Conference on Machine Learning,
Honolulu, Hawaii, USA.
mla: Hotegni, Sedjro Salomon, et al. “Approximation Algorithms for Fair Range Clustering.”
Proceedings of the 40th International Conference on Machine Learning, Honolulu,
Hawaii, USA. PMLR 202, 2023.
short: 'S.S. Hotegni, S. Mahabadi, A. Vakilian, in: Proceedings of the 40th International
Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023., n.d.'
conference:
end_date: 2023-07-29
location: Honolulu, Hawaii, USA
name: International Conference on Machine Learning
start_date: 2023-07-23
date_created: 2023-06-20T22:29:33Z
date_updated: 2023-06-20T23:03:12Z
department:
- _id: '655'
keyword:
- Fair range clustering
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openreview.net/forum?id=gBoKJT5JhM
oa: '1'
publication: Proceedings of the 40th International Conference on Machine Learning,
Honolulu, Hawaii, USA. PMLR 202, 2023.
publication_status: accepted
status: public
title: Approximation Algorithms for Fair Range Clustering
type: conference
user_id: '97995'
year: '2023'
...