---
_id: '48847'
abstract:
- lang: eng
text: Dynamic optimization problems have gained significant attention in evolutionary
computation as evolutionary algorithms (EAs) can easily adapt to changing environments.
We show that EAs can solve the graph coloring problem for bipartite graphs more
efficiently by using dynamic optimization. In our approach the graph instance
is given incrementally such that the EA can reoptimize its coloring when a new
edge introduces a conflict. We show that, when edges are inserted in a way that
preserves graph connectivity, Randomized Local Search (RLS) efficiently finds
a proper 2-coloring for all bipartite graphs. This includes graphs for which RLS
and other EAs need exponential expected time in a static optimization scenario.
We investigate different ways of building up the graph by popular graph traversals
such as breadth-first-search and depth-first-search and analyse the resulting
runtime behavior. We further show that offspring populations (e. g. a (1 + {$\lambda$})
RLS) lead to an exponential speedup in {$\lambda$}. Finally, an island model using
3 islands succeeds in an optimal time of {$\Theta$}(m) on every m-edge bipartite
graph, outperforming offspring populations. This is the first example where an
island model guarantees a speedup that is not bounded in the number of islands.
author:
- first_name: Jakob
full_name: Bossek, Jakob
id: '102979'
last_name: Bossek
orcid: 0000-0002-4121-4668
- first_name: Frank
full_name: Neumann, Frank
last_name: Neumann
- first_name: Pan
full_name: Peng, Pan
last_name: Peng
- first_name: Dirk
full_name: Sudholt, Dirk
last_name: Sudholt
citation:
ama: 'Bossek J, Neumann F, Peng P, Sudholt D. More Effective Randomized Search Heuristics
for Graph Coloring through Dynamic Optimization. In: Proceedings of the Genetic
and Evolutionary Computation Conference. GECCO ’20. Association for Computing
Machinery; 2020:1277–1285. doi:10.1145/3377930.3390174'
apa: Bossek, J., Neumann, F., Peng, P., & Sudholt, D. (2020). More Effective
Randomized Search Heuristics for Graph Coloring through Dynamic Optimization.
Proceedings of the Genetic and Evolutionary Computation Conference, 1277–1285.
https://doi.org/10.1145/3377930.3390174
bibtex: '@inproceedings{Bossek_Neumann_Peng_Sudholt_2020, place={New York, NY, USA},
series={GECCO ’20}, title={More Effective Randomized Search Heuristics for Graph
Coloring through Dynamic Optimization}, DOI={10.1145/3377930.3390174},
booktitle={Proceedings of the Genetic and Evolutionary Computation Conference},
publisher={Association for Computing Machinery}, author={Bossek, Jakob and Neumann,
Frank and Peng, Pan and Sudholt, Dirk}, year={2020}, pages={1277–1285}, collection={GECCO
’20} }'
chicago: 'Bossek, Jakob, Frank Neumann, Pan Peng, and Dirk Sudholt. “More Effective
Randomized Search Heuristics for Graph Coloring through Dynamic Optimization.”
In Proceedings of the Genetic and Evolutionary Computation Conference,
1277–1285. GECCO ’20. New York, NY, USA: Association for Computing Machinery,
2020. https://doi.org/10.1145/3377930.3390174.'
ieee: 'J. Bossek, F. Neumann, P. Peng, and D. Sudholt, “More Effective Randomized
Search Heuristics for Graph Coloring through Dynamic Optimization,” in Proceedings
of the Genetic and Evolutionary Computation Conference, 2020, pp. 1277–1285,
doi: 10.1145/3377930.3390174.'
mla: Bossek, Jakob, et al. “More Effective Randomized Search Heuristics for Graph
Coloring through Dynamic Optimization.” Proceedings of the Genetic and Evolutionary
Computation Conference, Association for Computing Machinery, 2020, pp. 1277–1285,
doi:10.1145/3377930.3390174.
short: 'J. Bossek, F. Neumann, P. Peng, D. Sudholt, in: Proceedings of the Genetic
and Evolutionary Computation Conference, Association for Computing Machinery,
New York, NY, USA, 2020, pp. 1277–1285.'
date_created: 2023-11-14T15:58:53Z
date_updated: 2023-12-13T10:43:41Z
department:
- _id: '819'
doi: 10.1145/3377930.3390174
extern: '1'
keyword:
- dynamic optimization
- evolutionary algorithms
- running time analysis
- theory
language:
- iso: eng
page: 1277–1285
place: New York, NY, USA
publication: Proceedings of the Genetic and Evolutionary Computation Conference
publication_identifier:
isbn:
- 978-1-4503-7128-5
publication_status: published
publisher: Association for Computing Machinery
series_title: GECCO ’20
status: public
title: More Effective Randomized Search Heuristics for Graph Coloring through Dynamic
Optimization
type: conference
user_id: '102979'
year: '2020'
...
---
_id: '24250'
author:
- first_name: Elmar
full_name: Moritzer, Elmar
id: '20531'
last_name: Moritzer
- first_name: Frederik Marvin
full_name: Mühlhoff, Frederik Marvin
id: '41312'
last_name: Mühlhoff
- first_name: Erhard
full_name: Krampe, Erhard
last_name: Krampe
- first_name: Birte
full_name: Böhnke, Birte
last_name: Böhnke
citation:
ama: Moritzer E, Mühlhoff FM, Krampe E, Böhnke B. More Material Combinations, Lower
Costs. Kunststoffe international. Published online 2020:22-25.
apa: Moritzer, E., Mühlhoff, F. M., Krampe, E., & Böhnke, B. (2020). More Material
Combinations, Lower Costs. Kunststoffe International, 22–25.
bibtex: '@article{Moritzer_Mühlhoff_Krampe_Böhnke_2020, title={More Material Combinations,
Lower Costs}, journal={Kunststoffe international}, author={Moritzer, Elmar and
Mühlhoff, Frederik Marvin and Krampe, Erhard and Böhnke, Birte}, year={2020},
pages={22–25} }'
chicago: Moritzer, Elmar, Frederik Marvin Mühlhoff, Erhard Krampe, and Birte Böhnke.
“More Material Combinations, Lower Costs.” Kunststoffe International, 2020,
22–25.
ieee: E. Moritzer, F. M. Mühlhoff, E. Krampe, and B. Böhnke, “More Material Combinations,
Lower Costs,” Kunststoffe international, pp. 22–25, 2020.
mla: Moritzer, Elmar, et al. “More Material Combinations, Lower Costs.” Kunststoffe
International, 2020, pp. 22–25.
short: E. Moritzer, F.M. Mühlhoff, E. Krampe, B. Böhnke, Kunststoffe International
(2020) 22–25.
date_created: 2021-09-13T09:09:36Z
date_updated: 2022-01-06T06:56:13Z
department:
- _id: '9'
- _id: '367'
- _id: '321'
language:
- iso: eng
page: 22-25
publication: Kunststoffe international
status: public
title: More Material Combinations, Lower Costs
type: journal_article
user_id: '44116'
year: '2020'
...
---
_id: '35701'
author:
- first_name: Steffen
full_name: Lünne, Steffen
last_name: Lünne
- first_name: Susanne
full_name: Schnell, Susanne
last_name: Schnell
- first_name: Rolf
full_name: Biehler, Rolf
id: '16274'
last_name: Biehler
citation:
ama: Lünne S, Schnell S, Biehler R. Motivation of out-of-field teachers for participating
in professional development courses in mathematics. European Journal of Teacher
Education. 2020;44(5):688-705. doi:10.1080/02619768.2020.1793950
apa: Lünne, S., Schnell, S., & Biehler, R. (2020). Motivation of out-of-field
teachers for participating in professional development courses in mathematics.
European Journal of Teacher Education, 44(5), 688–705. https://doi.org/10.1080/02619768.2020.1793950
bibtex: '@article{Lünne_Schnell_Biehler_2020, title={Motivation of out-of-field
teachers for participating in professional development courses in mathematics},
volume={44}, DOI={10.1080/02619768.2020.1793950},
number={5}, journal={European Journal of Teacher Education}, publisher={Informa
UK Limited}, author={Lünne, Steffen and Schnell, Susanne and Biehler, Rolf}, year={2020},
pages={688–705} }'
chicago: 'Lünne, Steffen, Susanne Schnell, and Rolf Biehler. “Motivation of Out-of-Field
Teachers for Participating in Professional Development Courses in Mathematics.”
European Journal of Teacher Education 44, no. 5 (2020): 688–705. https://doi.org/10.1080/02619768.2020.1793950.'
ieee: 'S. Lünne, S. Schnell, and R. Biehler, “Motivation of out-of-field teachers
for participating in professional development courses in mathematics,” European
Journal of Teacher Education, vol. 44, no. 5, pp. 688–705, 2020, doi: 10.1080/02619768.2020.1793950.'
mla: Lünne, Steffen, et al. “Motivation of Out-of-Field Teachers for Participating
in Professional Development Courses in Mathematics.” European Journal of Teacher
Education, vol. 44, no. 5, Informa UK Limited, 2020, pp. 688–705, doi:10.1080/02619768.2020.1793950.
short: S. Lünne, S. Schnell, R. Biehler, European Journal of Teacher Education 44
(2020) 688–705.
date_created: 2023-01-10T09:08:17Z
date_updated: 2023-01-11T10:18:30Z
department:
- _id: '34'
- _id: '10'
- _id: '97'
- _id: '363'
doi: 10.1080/02619768.2020.1793950
intvolume: ' 44'
issue: '5'
keyword:
- Education
language:
- iso: eng
page: 688-705
publication: European Journal of Teacher Education
publication_identifier:
issn:
- 0261-9768
- 1469-5928
publication_status: published
publisher: Informa UK Limited
status: public
title: Motivation of out-of-field teachers for participating in professional development
courses in mathematics
type: journal_article
user_id: '37888'
volume: 44
year: '2020'
...
---
_id: '35298'
abstract:
- lang: ger
text: Im Artikel werden drei verschiedene Lernzugänge (kom-petenzorientiertes, ästhetisches und biographisches Lernen) vorgestellt und aus
theoretischer Perspektive deren motivierender Gehalt für selbstreguliertes Lernen
in Praxisphasen des Lehramtsstudiumsherausgearbeitet. Als theoretische Grund-lage
dient die Selbstbestimmungstheorie als zentrale motivationale Theorie zur Erklärung
selbstbestimmten Handelns.
- lang: eng
text: The article addresses how motivational learning approaches (competency-oriented, aesthetic and biographical) can contribute to the professionalization
of preservice teachers during a long-term internship. As a theoretical basis,
the self-determination theory serves as a central motivational theory for explaining
self-determined action.
alternative_title:
- Ein Blick auf kompetenzorientiertes, ästhetisches und biographisches Lernen im Lehramtsstudium
author:
- first_name: Carina
full_name: Caruso, Carina
id: '23123'
last_name: Caruso
- first_name: Christine
full_name: Adammek, Christine
last_name: Adammek
- first_name: Sabrina
full_name: Bonanati, Sabrina
last_name: Bonanati
- first_name: Sybille
full_name: Wiescholek, Sybille
last_name: Wiescholek
citation:
ama: Caruso C, Adammek C, Bonanati S, Wiescholek S. Motivierende Lernzugänge als
Ausgangspunkt der Professionalisierung angehender Lehrer_innen. Herausforderung
Lehrer*innenbildung - Zeitschrift Zur Konzeption, Gestaltung Und Diskussion.
2020;3(1):18-33. doi:10.4119/hlz-2540
apa: Caruso, C., Adammek, C., Bonanati, S., & Wiescholek, S. (2020). Motivierende
Lernzugänge als Ausgangspunkt der Professionalisierung angehender Lehrer_innen.
Herausforderung Lehrer*innenbildung - Zeitschrift Zur Konzeption, Gestaltung
Und Diskussion, 3(1), 18–33. https://doi.org/10.4119/hlz-2540
bibtex: '@article{Caruso_Adammek_Bonanati_Wiescholek_2020, title={Motivierende Lernzugänge
als Ausgangspunkt der Professionalisierung angehender Lehrer_innen}, volume={3},
DOI={10.4119/hlz-2540}, number={1},
journal={Herausforderung Lehrer*innenbildung - Zeitschrift Zur Konzeption, Gestaltung
Und Diskussion}, author={Caruso, Carina and Adammek, Christine and Bonanati, Sabrina
and Wiescholek, Sybille}, year={2020}, pages={18–33} }'
chicago: 'Caruso, Carina, Christine Adammek, Sabrina Bonanati, and Sybille Wiescholek.
“Motivierende Lernzugänge als Ausgangspunkt der Professionalisierung angehender
Lehrer_innen.” Herausforderung Lehrer*innenbildung - Zeitschrift Zur Konzeption,
Gestaltung Und Diskussion 3, no. 1 (2020): 18–33. https://doi.org/10.4119/hlz-2540.'
ieee: 'C. Caruso, C. Adammek, S. Bonanati, and S. Wiescholek, “Motivierende Lernzugänge
als Ausgangspunkt der Professionalisierung angehender Lehrer_innen,” Herausforderung
Lehrer*innenbildung - Zeitschrift Zur Konzeption, Gestaltung Und Diskussion,
vol. 3, no. 1, pp. 18–33, 2020, doi: 10.4119/hlz-2540.'
mla: Caruso, Carina, et al. “Motivierende Lernzugänge als Ausgangspunkt der Professionalisierung
angehender Lehrer_innen.” Herausforderung Lehrer*innenbildung - Zeitschrift
Zur Konzeption, Gestaltung Und Diskussion, vol. 3, no. 1, 2020, pp. 18–33,
doi:10.4119/hlz-2540.
short: C. Caruso, C. Adammek, S. Bonanati, S. Wiescholek, Herausforderung Lehrer*innenbildung
- Zeitschrift Zur Konzeption, Gestaltung Und Diskussion 3 (2020) 18–33.
date_created: 2023-01-05T13:58:28Z
date_updated: 2023-01-06T12:18:16Z
doi: 10.4119/hlz-2540
intvolume: ' 3'
issue: '1'
keyword:
- ästhetische Forschung
- Biographiearbeit
- Praxissemester
- Professionalisierung
- selbstreguliertes Lernen
- Motivation / aesthetic research
- biographical work
- long-term internship
- profes-sionalization
- self-regulated learning
- motivation
language:
- iso: other
page: 18-33
publication: Herausforderung Lehrer*innenbildung - Zeitschrift Zur Konzeption, Gestaltung
Und Diskussion
publication_identifier:
issn:
- 2625-0675
publication_status: published
status: public
title: Motivierende Lernzugänge als Ausgangspunkt der Professionalisierung angehender
Lehrer_innen
type: journal_article
user_id: '86519'
volume: 3
year: '2020'
...
---
_id: '21536'
abstract:
- lang: eng
text: "We consider a resource-aware variant of the classical multi-armed bandit\r\nproblem:
In each round, the learner selects an arm and determines a resource\r\nlimit.
It then observes a corresponding (random) reward, provided the (random)\r\namount
of consumed resources remains below the limit. Otherwise, the\r\nobservation is
censored, i.e., no reward is obtained. For this problem setting,\r\nwe introduce
a measure of regret, which incorporates the actual amount of\r\nallocated resources
of each learning round as well as the optimality of\r\nrealizable rewards. Thus,
to minimize regret, the learner needs to set a\r\nresource limit and choose an
arm in such a way that the chance to realize a\r\nhigh reward within the predefined
resource limit is high, while the resource\r\nlimit itself should be kept as low
as possible. We derive the theoretical lower\r\nbound on the cumulative regret
and propose a learning algorithm having a regret\r\nupper bound that matches the
lower bound. In a simulation study, we show that\r\nour learning algorithm outperforms
straightforward extensions of standard\r\nmulti-armed bandit algorithms."
author:
- first_name: Viktor
full_name: Bengs, Viktor
last_name: Bengs
- first_name: Eyke
full_name: Hüllermeier, Eyke
last_name: Hüllermeier
citation:
ama: Bengs V, Hüllermeier E. Multi-Armed Bandits with Censored Consumption of Resources.
arXiv:201100813. 2020.
apa: Bengs, V., & Hüllermeier, E. (2020). Multi-Armed Bandits with Censored
Consumption of Resources. ArXiv:2011.00813.
bibtex: '@article{Bengs_Hüllermeier_2020, title={Multi-Armed Bandits with Censored
Consumption of Resources}, journal={arXiv:2011.00813}, author={Bengs, Viktor and
Hüllermeier, Eyke}, year={2020} }'
chicago: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored
Consumption of Resources.” ArXiv:2011.00813, 2020.
ieee: V. Bengs and E. Hüllermeier, “Multi-Armed Bandits with Censored Consumption
of Resources,” arXiv:2011.00813. 2020.
mla: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption
of Resources.” ArXiv:2011.00813, 2020.
short: V. Bengs, E. Hüllermeier, ArXiv:2011.00813 (2020).
date_created: 2021-03-18T11:27:37Z
date_updated: 2022-01-06T06:55:03Z
department:
- _id: '34'
- _id: '7'
- _id: '355'
language:
- iso: eng
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: arXiv:2011.00813
status: public
title: Multi-Armed Bandits with Censored Consumption of Resources
type: preprint
user_id: '76599'
year: '2020'
...
---
_id: '32242'
abstract:
- lang: eng
text: "We consider a resource-aware variant of the classical multi-armed bandit\r\nproblem:
In each round, the learner selects an arm and determines a resource\r\nlimit.
It then observes a corresponding (random) reward, provided the (random)\r\namount
of consumed resources remains below the limit. Otherwise, the\r\nobservation is
censored, i.e., no reward is obtained. For this problem setting,\r\nwe introduce
a measure of regret, which incorporates the actual amount of\r\nallocated resources
of each learning round as well as the optimality of\r\nrealizable rewards. Thus,
to minimize regret, the learner needs to set a\r\nresource limit and choose an
arm in such a way that the chance to realize a\r\nhigh reward within the predefined
resource limit is high, while the resource\r\nlimit itself should be kept as low
as possible. We derive the theoretical lower\r\nbound on the cumulative regret
and propose a learning algorithm having a regret\r\nupper bound that matches the
lower bound. In a simulation study, we show that\r\nour learning algorithm outperforms
straightforward extensions of standard\r\nmulti-armed bandit algorithms."
author:
- first_name: Viktor
full_name: Bengs, Viktor
last_name: Bengs
- first_name: Eyke
full_name: Hüllermeier, Eyke
last_name: Hüllermeier
citation:
ama: Bengs V, Hüllermeier E. Multi-Armed Bandits with Censored Consumption of Resources.
arXiv:201100813. Published online 2020.
apa: Bengs, V., & Hüllermeier, E. (2020). Multi-Armed Bandits with Censored
Consumption of Resources. In arXiv:2011.00813.
bibtex: '@article{Bengs_Hüllermeier_2020, title={Multi-Armed Bandits with Censored
Consumption of Resources}, journal={arXiv:2011.00813}, author={Bengs, Viktor and
Hüllermeier, Eyke}, year={2020} }'
chicago: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored
Consumption of Resources.” ArXiv:2011.00813, 2020.
ieee: V. Bengs and E. Hüllermeier, “Multi-Armed Bandits with Censored Consumption
of Resources,” arXiv:2011.00813. 2020.
mla: Bengs, Viktor, and Eyke Hüllermeier. “Multi-Armed Bandits with Censored Consumption
of Resources.” ArXiv:2011.00813, 2020.
short: V. Bengs, E. Hüllermeier, ArXiv:2011.00813 (2020).
date_created: 2022-06-28T07:26:54Z
date_updated: 2022-06-28T07:27:19Z
department:
- _id: '27'
external_id:
arxiv:
- '2011.00813'
language:
- iso: eng
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: arXiv:2011.00813
status: public
title: Multi-Armed Bandits with Censored Consumption of Resources
type: preprint
user_id: '15278'
year: '2020'
...
---
_id: '16280'
abstract:
- lang: eng
text: 'Assigning bands of the wireless spectrum as resources to users is a common
problem in wireless networks. Typically, frequency bands were assumed to be available
in a stable manner. Nevertheless, in recent scenarios where wireless networks
may be deployed in unknown environments, spectrum competition is considered, making
it uncertain whether a frequency band is available at all or at what quality.
To fully exploit such resources with uncertain availability, the multi-armed bandit
(MAB) method, a representative online learning technique, has been applied to
design spectrum scheduling algorithms. This article surveys such proposals. We
describe the following three aspects: how to model spectrum scheduling problems
within the MAB framework, what the main thread is following which prevalent algorithms
are designed, and how to evaluate algorithm performance and complexity. We also
give some promising directions for future research in related fields.'
author:
- first_name: Feng
full_name: Li, Feng
last_name: Li
- first_name: Dongxiao
full_name: Yu, Dongxiao
last_name: Yu
- first_name: Huan
full_name: Yang, Huan
last_name: Yang
- first_name: Jiguo
full_name: Yu, Jiguo
last_name: Yu
- first_name: Holger
full_name: Karl, Holger
id: '126'
last_name: Karl
- first_name: Xiuzhen
full_name: Cheng, Xiuzhen
last_name: Cheng
citation:
ama: 'Li F, Yu D, Yang H, Yu J, Karl H, Cheng X. Multi-Armed-Bandit-Based Spectrum
Scheduling Algorithms in Wireless Networks: A Survey. IEEE Wireless Communications.
2020:24-30. doi:10.1109/mwc.001.1900280'
apa: 'Li, F., Yu, D., Yang, H., Yu, J., Karl, H., & Cheng, X. (2020). Multi-Armed-Bandit-Based
Spectrum Scheduling Algorithms in Wireless Networks: A Survey. IEEE Wireless
Communications, 24–30. https://doi.org/10.1109/mwc.001.1900280'
bibtex: '@article{Li_Yu_Yang_Yu_Karl_Cheng_2020, title={Multi-Armed-Bandit-Based
Spectrum Scheduling Algorithms in Wireless Networks: A Survey}, DOI={10.1109/mwc.001.1900280},
journal={IEEE Wireless Communications}, author={Li, Feng and Yu, Dongxiao and
Yang, Huan and Yu, Jiguo and Karl, Holger and Cheng, Xiuzhen}, year={2020}, pages={24–30}
}'
chicago: 'Li, Feng, Dongxiao Yu, Huan Yang, Jiguo Yu, Holger Karl, and Xiuzhen Cheng.
“Multi-Armed-Bandit-Based Spectrum Scheduling Algorithms in Wireless Networks:
A Survey.” IEEE Wireless Communications, 2020, 24–30. https://doi.org/10.1109/mwc.001.1900280.'
ieee: 'F. Li, D. Yu, H. Yang, J. Yu, H. Karl, and X. Cheng, “Multi-Armed-Bandit-Based
Spectrum Scheduling Algorithms in Wireless Networks: A Survey,” IEEE Wireless
Communications, pp. 24–30, 2020.'
mla: 'Li, Feng, et al. “Multi-Armed-Bandit-Based Spectrum Scheduling Algorithms
in Wireless Networks: A Survey.” IEEE Wireless Communications, 2020, pp.
24–30, doi:10.1109/mwc.001.1900280.'
short: F. Li, D. Yu, H. Yang, J. Yu, H. Karl, X. Cheng, IEEE Wireless Communications
(2020) 24–30.
date_created: 2020-03-10T16:02:30Z
date_updated: 2022-01-06T06:52:48Z
department:
- _id: '75'
doi: 10.1109/mwc.001.1900280
language:
- iso: eng
page: 24-30
publication: IEEE Wireless Communications
publication_identifier:
issn:
- 1536-1284
- 1558-0687
publication_status: published
status: public
title: 'Multi-Armed-Bandit-Based Spectrum Scheduling Algorithms in Wireless Networks:
A Survey'
type: journal_article
user_id: '126'
year: '2020'
...
---
_id: '15025'
abstract:
- lang: eng
text: In software engineering, the imprecise requirements of a user are transformed
to a formal requirements specification during the requirements elicitation process.
This process is usually guided by requirements engineers interviewing the user.
We want to partially automate this first step of the software engineering process
in order to enable users to specify a desired software system on their own. With
our approach, users are only asked to provide exemplary behavioral descriptions.
The problem of synthesizing a requirements specification from examples can partially
be reduced to the problem of grammatical inference, to which we apply an active
coevolutionary learning approach. However, this approach would usually require
many feedback queries to be sent to the user. In this work, we extend and generalize
our active learning approach to receive knowledge from multiple oracles, also
known as proactive learning. The ‘user oracle’ represents input received from
the user and the ‘knowledge oracle’ represents available, formalized domain knowledge.
We call our two-oracle approach the ‘first apply knowledge then query’ (FAKT/Q)
algorithm. We compare FAKT/Q to the active learning approach and provide an extensive
benchmark evaluation. As result we find that the number of required user queries
is reduced and the inference process is sped up significantly. Finally, with so-called
On-The-Fly Markets, we present a motivation and an application of our approach
where such knowledge is available.
author:
- first_name: Marcel Dominik
full_name: Wever, Marcel Dominik
id: '33176'
last_name: Wever
orcid: ' https://orcid.org/0000-0001-9782-6818'
- first_name: Lorijn
full_name: van Rooijen, Lorijn
id: '58843'
last_name: van Rooijen
- first_name: Heiko
full_name: Hamann, Heiko
last_name: Hamann
citation:
ama: Wever MD, van Rooijen L, Hamann H. Multi-Oracle Coevolutionary Learning of
Requirements Specifications from Examples in On-The-Fly Markets. Evolutionary
Computation. 2020;28(2):165–193. doi:10.1162/evco_a_00266
apa: Wever, M. D., van Rooijen, L., & Hamann, H. (2020). Multi-Oracle Coevolutionary
Learning of Requirements Specifications from Examples in On-The-Fly Markets. Evolutionary
Computation, 28(2), 165–193. https://doi.org/10.1162/evco_a_00266
bibtex: '@article{Wever_van Rooijen_Hamann_2020, title={Multi-Oracle Coevolutionary
Learning of Requirements Specifications from Examples in On-The-Fly Markets},
volume={28}, DOI={10.1162/evco_a_00266},
number={2}, journal={Evolutionary Computation}, publisher={MIT Press Journals},
author={Wever, Marcel Dominik and van Rooijen, Lorijn and Hamann, Heiko}, year={2020},
pages={165–193} }'
chicago: 'Wever, Marcel Dominik, Lorijn van Rooijen, and Heiko Hamann. “Multi-Oracle
Coevolutionary Learning of Requirements Specifications from Examples in On-The-Fly
Markets.” Evolutionary Computation 28, no. 2 (2020): 165–193. https://doi.org/10.1162/evco_a_00266.'
ieee: 'M. D. Wever, L. van Rooijen, and H. Hamann, “Multi-Oracle Coevolutionary
Learning of Requirements Specifications from Examples in On-The-Fly Markets,”
Evolutionary Computation, vol. 28, no. 2, pp. 165–193, 2020, doi: 10.1162/evco_a_00266.'
mla: Wever, Marcel Dominik, et al. “Multi-Oracle Coevolutionary Learning of Requirements
Specifications from Examples in On-The-Fly Markets.” Evolutionary Computation,
vol. 28, no. 2, MIT Press Journals, 2020, pp. 165–193, doi:10.1162/evco_a_00266.
short: M.D. Wever, L. van Rooijen, H. Hamann, Evolutionary Computation 28 (2020)
165–193.
date_created: 2019-11-18T14:19:19Z
date_updated: 2022-01-06T06:52:15Z
department:
- _id: '34'
- _id: '355'
- _id: '26'
- _id: '63'
- _id: '238'
doi: 10.1162/evco_a_00266
intvolume: ' 28'
issue: '2'
language:
- iso: eng
page: 165–193
project:
- _id: '1'
name: SFB 901
- _id: '3'
name: SFB 901 - Project Area B
- _id: '9'
name: SFB 901 - Subproject B1
- _id: '10'
name: SFB 901 - Subproject B2
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Evolutionary Computation
publication_status: published
publisher: MIT Press Journals
related_material:
link:
- relation: confirmation
url: https://www.mitpressjournals.org/doi/pdf/10.1162/evco_a_00266
status: public
title: Multi-Oracle Coevolutionary Learning of Requirements Specifications from Examples
in On-The-Fly Markets
type: journal_article
user_id: '15415'
volume: 28
year: '2020'
...
---
_id: '20766'
abstract:
- lang: eng
text: Recently, the source separation performance was greatly improved by time-domain
audio source separation based on dual-path recurrent neural network (DPRNN). DPRNN
is a simple but effective model for a long sequential data. While DPRNN is quite
efficient in modeling a sequential data of the length of an utterance, i.e., about
5 to 10 second data, it is harder to apply it to longer sequences such as whole
conversations consisting of multiple utterances. It is simply because, in such
a case, the number of time steps consumed by its internal module called inter-chunk
RNN becomes extremely large. To mitigate this problem, this paper proposes a multi-path
RNN (MPRNN), a generalized version of DPRNN, that models the input data in a hierarchical
manner. In the MPRNN framework, the input data is represented at several (>_ 3)
time-resolutions, each of which is modeled by a specific RNN sub-module. For example,
the RNN sub-module that deals with the finest resolution may model temporal relationship
only within a phoneme, while the RNN sub-module handling the most coarse resolution
may capture only the relationship between utterances such as speaker information.
We perform experiments using simulated dialogue-like mixtures and show that MPRNN
has greater model capacity, and it outperforms the current state-of-the-art DPRNN
framework especially in online processing scenarios.
author:
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Tomohiro
full_name: Nakatani, Tomohiro
last_name: Nakatani
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Kinoshita K, von Neumann T, Delcroix M, Nakatani T, Haeb-Umbach R. Multi-Path
RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker
Stream Separation. In: Proc. Interspeech 2020. ; 2020:2652-2656. doi:10.21437/Interspeech.2020-2388'
apa: Kinoshita, K., von Neumann, T., Delcroix, M., Nakatani, T., & Haeb-Umbach,
R. (2020). Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and
its Application to Speaker Stream Separation. Proc. Interspeech 2020, 2652–2656.
https://doi.org/10.21437/Interspeech.2020-2388
bibtex: '@inproceedings{Kinoshita_von Neumann_Delcroix_Nakatani_Haeb-Umbach_2020,
title={Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its
Application to Speaker Stream Separation}, DOI={10.21437/Interspeech.2020-2388},
booktitle={Proc. Interspeech 2020}, author={Kinoshita, Keisuke and von Neumann,
Thilo and Delcroix, Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2020},
pages={2652–2656} }'
chicago: Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Tomohiro Nakatani,
and Reinhold Haeb-Umbach. “Multi-Path RNN for Hierarchical Modeling of Long Sequential
Data and Its Application to Speaker Stream Separation.” In Proc. Interspeech
2020, 2652–56, 2020. https://doi.org/10.21437/Interspeech.2020-2388.
ieee: 'K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, and R. Haeb-Umbach,
“Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application
to Speaker Stream Separation,” in Proc. Interspeech 2020, 2020, pp. 2652–2656,
doi: 10.21437/Interspeech.2020-2388.'
mla: Kinoshita, Keisuke, et al. “Multi-Path RNN for Hierarchical Modeling of Long
Sequential Data and Its Application to Speaker Stream Separation.” Proc. Interspeech
2020, 2020, pp. 2652–56, doi:10.21437/Interspeech.2020-2388.
short: 'K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, R. Haeb-Umbach,
in: Proc. Interspeech 2020, 2020, pp. 2652–2656.'
date_created: 2020-12-16T14:15:24Z
date_updated: 2023-11-15T12:14:25Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/Interspeech.2020-2388
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T14:16:32Z
date_updated: 2020-12-16T14:16:32Z
file_id: '20767'
file_name: INTERSPEECH_2020_vonNeumann1_Paper.pdf
file_size: 1725219
relation: main_file
file_date_updated: 2020-12-16T14:16:32Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 2652-2656
publication: Proc. Interspeech 2020
quality_controlled: '1'
status: public
title: Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application
to Speaker Stream Separation
type: conference
user_id: '49870'
year: '2020'
...
---
_id: '20764'
abstract:
- lang: eng
text: 'Most approaches to multi-talker overlapped speech separation and recognition
assume that the number of simultaneously active speakers is given, but in realistic
situations, it is typically unknown. To cope with this, we extend an iterative
speech extraction system with mechanisms to count the number of sources and combine
it with a single-talker speech recognizer to form the first end-to-end multi-talker
automatic speech recognition system for an unknown number of active speakers.
Our experiments show very promising performance in counting accuracy, source separation
and speech recognition on simulated clean mixtures from WSJ0-2mix and WSJ0-3mix.
Among others, we set a new state-of-the-art word error rate on the WSJ0-2mix database.
Furthermore, our system generalizes well to a larger number of speakers than it
ever saw during training, as shown in experiments with the WSJ0-4mix database. '
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Lukas
full_name: Drude, Lukas
last_name: Drude
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Tomohiro
full_name: Nakatani, Tomohiro
last_name: Nakatani
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Drude L, et al. Multi-Talker ASR for an Unknown
Number of Sources: Joint Training of Source Counting, Separation and ASR. In:
Proc. Interspeech 2020. ; 2020:3097-3101. doi:10.21437/Interspeech.2020-2519'
apa: 'von Neumann, T., Boeddeker, C., Drude, L., Kinoshita, K., Delcroix, M., Nakatani,
T., & Haeb-Umbach, R. (2020). Multi-Talker ASR for an Unknown Number of Sources:
Joint Training of Source Counting, Separation and ASR. Proc. Interspeech 2020,
3097–3101. https://doi.org/10.21437/Interspeech.2020-2519'
bibtex: '@inproceedings{von Neumann_Boeddeker_Drude_Kinoshita_Delcroix_Nakatani_Haeb-Umbach_2020,
title={Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source
Counting, Separation and ASR}, DOI={10.21437/Interspeech.2020-2519},
booktitle={Proc. Interspeech 2020}, author={von Neumann, Thilo and Boeddeker,
Christoph and Drude, Lukas and Kinoshita, Keisuke and Delcroix, Marc and Nakatani,
Tomohiro and Haeb-Umbach, Reinhold}, year={2020}, pages={3097–3101} }'
chicago: 'Neumann, Thilo von, Christoph Boeddeker, Lukas Drude, Keisuke Kinoshita,
Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Multi-Talker ASR
for an Unknown Number of Sources: Joint Training of Source Counting, Separation
and ASR.” In Proc. Interspeech 2020, 3097–3101, 2020. https://doi.org/10.21437/Interspeech.2020-2519.'
ieee: 'T. von Neumann et al., “Multi-Talker ASR for an Unknown Number of
Sources: Joint Training of Source Counting, Separation and ASR,” in Proc. Interspeech
2020, 2020, pp. 3097–3101, doi: 10.21437/Interspeech.2020-2519.'
mla: 'von Neumann, Thilo, et al. “Multi-Talker ASR for an Unknown Number of Sources:
Joint Training of Source Counting, Separation and ASR.” Proc. Interspeech 2020,
2020, pp. 3097–101, doi:10.21437/Interspeech.2020-2519.'
short: 'T. von Neumann, C. Boeddeker, L. Drude, K. Kinoshita, M. Delcroix, T. Nakatani,
R. Haeb-Umbach, in: Proc. Interspeech 2020, 2020, pp. 3097–3101.'
date_created: 2020-12-16T14:12:45Z
date_updated: 2023-11-15T12:17:57Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/Interspeech.2020-2519
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T14:14:14Z
date_updated: 2020-12-16T14:14:14Z
file_id: '20765'
file_name: INTERSPEECH_2020_vonNeumann_Paper.pdf
file_size: 267893
relation: main_file
file_date_updated: 2020-12-16T14:14:14Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 3097-3101
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. Interspeech 2020
quality_controlled: '1'
status: public
title: 'Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source
Counting, Separation and ASR'
type: conference
user_id: '49870'
year: '2020'
...