Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Zhang, H.; Xu, Y.; Tian, Y.; Li, Y.; Falk, T. H.; Wang, F. -Y.
Selective Shift: Towards Personalized Domain Adaptation in Multi-Agent Collaborative Perception Proceedings Article
In: MM - Proc. ACM Int. Conf. Multimedia, Co-Located with MM, pp. 886–895, Association for Computing Machinery, Inc, 2025, ISBN: 979-840072035-2 (ISBN), (Journal Abbreviation: MM - Proc. ACM Int. Conf. Multimedia, Co-Located with MM).
Abstract | Links | BibTeX | Tags: 3D object, 3D object detection, Adaptation methods, Adaptive alignment, Collaborative perception, Domain adaptation, Entropy, Intelligent agents, Multi agent, Multi agent systems, Object detection, Object recognition, Objects detection, Relational semantics, Semantics, uncertainty
@inproceedings{zhangSelectiveShiftPersonalized2025,
title = {Selective Shift: Towards Personalized Domain Adaptation in Multi-Agent Collaborative Perception},
author = {H. Zhang and Y. Xu and Y. Tian and Y. Li and T. H. Falk and F. -Y. Wang},
url = {https://www.scopus.com/pages/publications/105024076483?origin=resultslist},
doi = {10.1145/3746027.3754723},
isbn = {979-840072035-2 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {MM - Proc. ACM Int. Conf. Multimedia, Co-Located with MM},
pages = {886–895},
publisher = {Association for Computing Machinery, Inc},
abstract = {Given the scarcity of real data and the time-intensive nature of labeling, current multi-agent perception models often rely on simulated sensor data for training and validation. However, perception performance deteriorates significantly due to domain gap between simulated and real data. Existing adaptation methods focus on domain-generalized feature extraction while neglecting multi-agent shift uncertainty and relational semantic loss. To address this issue, we propose a Selective Shift Domain Adaptation method in multi-agent collaborative perception, called SSDA. SSDA incorporates two essential components: the frequency-decoupled feature shift adjustment (FSA) and the entropy-driven staged adaptive alignment (SAA). To mitigate the relational semantic loss, the FSA is proposed to simplify the representation of correlation features and remove redundant information from the source domain, thereby mitigating interference for domain adversarial scenarios. To tackle the shift uncertainty, the SAA is designed to achieve adaptive alignment from global to local guided by information entropy, which dynamically adjusts weights for samples according to their level of uncertainty. The results demonstrate that the SSDA is significantly superior to the SOTA, achieving up to 7.35% improvements on AP@0.7. © 2025 ACM.},
note = {Journal Abbreviation: MM - Proc. ACM Int. Conf. Multimedia, Co-Located with MM},
keywords = {3D object, 3D object detection, Adaptation methods, Adaptive alignment, Collaborative perception, Domain adaptation, Entropy, Intelligent agents, Multi agent, Multi agent systems, Object detection, Object recognition, Objects detection, Relational semantics, Semantics, uncertainty},
pubstate = {published},
tppubtype = {inproceedings}
}
Given the scarcity of real data and the time-intensive nature of labeling, current multi-agent perception models often rely on simulated sensor data for training and validation. However, perception performance deteriorates significantly due to domain gap between simulated and real data. Existing adaptation methods focus on domain-generalized feature extraction while neglecting multi-agent shift uncertainty and relational semantic loss. To address this issue, we propose a Selective Shift Domain Adaptation method in multi-agent collaborative perception, called SSDA. SSDA incorporates two essential components: the frequency-decoupled feature shift adjustment (FSA) and the entropy-driven staged adaptive alignment (SAA). To mitigate the relational semantic loss, the FSA is proposed to simplify the representation of correlation features and remove redundant information from the source domain, thereby mitigating interference for domain adversarial scenarios. To tackle the shift uncertainty, the SAA is designed to achieve adaptive alignment from global to local guided by information entropy, which dynamically adjusts weights for samples according to their level of uncertainty. The results demonstrate that the SSDA is significantly superior to the SOTA, achieving up to 7.35% improvements on AP@0.7. © 2025 ACM.
2.
Papapanagiotou, P.; Manataki, A.; Davoust, A.; Kleek, M. Van; Robertson, D.; Murray-Rust, D.; Shadbolt, N.
Social machines for all: Blue sky ideas track Proceedings Article
In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, pp. 1208–1212, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2018, ISSN: 15488403, (ISSN: 15488403).
Abstract | Links | BibTeX | Tags: Agent based simulation, Analysis, Autonomous agents, Design, Development method, Distributed agents, Distributed computer systems, Easy-to-use systems, Economic and social effects, Electronic institutions, Intelligent agents, Model driven development, Model-driven Engineering, Models, Multi agent systems, Systems analysis
@inproceedings{papapanagiotou_social_2018,
title = {Social machines for all: Blue sky ideas track},
author = {P. Papapanagiotou and A. Manataki and A. Davoust and M. Van Kleek and D. Robertson and D. Murray-Rust and N. Shadbolt},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054668594&partnerID=40&md5=77eba348dbafa30aef9d016186b46804},
issn = {15488403},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS},
volume = {2},
pages = {1208–1212},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)},
abstract = {In today's interconnected world, people interact to a unprecedented degree through the use of digital platforms and services, forming complex 'social machines'. These are now homes to autonomous agents as well as people, providing an open space where human and computational intelligence can mingle-a new frontier for distributed agent systems. However, participants typically have limited autonomy to define and shape the machines they are part of. In this paper, we envision a future where individuals are able to develop their own Social Machines, enabling them to interact in a trustworthy, decentralized way. To make this possible, development methods and tools must see their barriers-to-entry dramatically lowered. People should be able to specify the agent roles and inte-raction patterns in an intuitive, visual way, analyse and test their designs and deploy them as easy to use systems. We argue that this is a challenging but realistic goal, which should be tackled by navigating the trade-off between the accessibility of the design methods -primarily the modelling formalisms- And their expressive power. We support our arguments by drawing ideas from different research areas including electronic institutions, agent-based simulation, process modelling, formal verification, and model-driven engineering. © 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.},
note = {ISSN: 15488403},
keywords = {Agent based simulation, Analysis, Autonomous agents, Design, Development method, Distributed agents, Distributed computer systems, Easy-to-use systems, Economic and social effects, Electronic institutions, Intelligent agents, Model driven development, Model-driven Engineering, Models, Multi agent systems, Systems analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In today's interconnected world, people interact to a unprecedented degree through the use of digital platforms and services, forming complex 'social machines'. These are now homes to autonomous agents as well as people, providing an open space where human and computational intelligence can mingle-a new frontier for distributed agent systems. However, participants typically have limited autonomy to define and shape the machines they are part of. In this paper, we envision a future where individuals are able to develop their own Social Machines, enabling them to interact in a trustworthy, decentralized way. To make this possible, development methods and tools must see their barriers-to-entry dramatically lowered. People should be able to specify the agent roles and inte-raction patterns in an intuitive, visual way, analyse and test their designs and deploy them as easy to use systems. We argue that this is a challenging but realistic goal, which should be tackled by navigating the trade-off between the accessibility of the design methods -primarily the modelling formalisms- And their expressive power. We support our arguments by drawing ideas from different research areas including electronic institutions, agent-based simulation, process modelling, formal verification, and model-driven engineering. © 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
3.
Papapanagiotou, P.; Manataki, A.; Davoust, A.; Kleek, M. Van; Robertson, D.; Murray-Rust, D.; Shadbolt, N.
Social machines for all: Blue sky ideas track Proceedings Article
In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, pp. 1208–1212, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2018, ISSN: 15488403.
Abstract | Links | BibTeX | Tags: Agent based simulation, Analysis, Autonomous agents, Design, Development method, Distributed agents, Distributed computer systems, Easy-to-use systems, Economic and social effects, Electronic institutions, Intelligent agents, Model driven development, Model-driven Engineering, Models, Multi agent systems, Systems analysis
@inproceedings{papapanagiotouSocialMachinesAll2018,
title = {Social machines for all: Blue sky ideas track},
author = {P. Papapanagiotou and A. Manataki and A. Davoust and M. Van Kleek and D. Robertson and D. Murray-Rust and N. Shadbolt},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054668594&partnerID=40&md5=77eba348dbafa30aef9d016186b46804},
issn = {15488403},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS},
volume = {2},
pages = {1208–1212},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)},
abstract = {In today's interconnected world, people interact to a unprecedented degree through the use of digital platforms and services, forming complex 'social machines'. These are now homes to autonomous agents as well as people, providing an open space where human and computational intelligence can mingle-a new frontier for distributed agent systems. However, participants typically have limited autonomy to define and shape the machines they are part of. In this paper, we envision a future where individuals are able to develop their own Social Machines, enabling them to interact in a trustworthy, decentralized way. To make this possible, development methods and tools must see their barriers-to-entry dramatically lowered. People should be able to specify the agent roles and inte-raction patterns in an intuitive, visual way, analyse and test their designs and deploy them as easy to use systems. We argue that this is a challenging but realistic goal, which should be tackled by navigating the trade-off between the accessibility of the design methods -primarily the modelling formalisms- And their expressive power. We support our arguments by drawing ideas from different research areas including electronic institutions, agent-based simulation, process modelling, formal verification, and model-driven engineering. © 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.},
keywords = {Agent based simulation, Analysis, Autonomous agents, Design, Development method, Distributed agents, Distributed computer systems, Easy-to-use systems, Economic and social effects, Electronic institutions, Intelligent agents, Model driven development, Model-driven Engineering, Models, Multi agent systems, Systems analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In today's interconnected world, people interact to a unprecedented degree through the use of digital platforms and services, forming complex 'social machines'. These are now homes to autonomous agents as well as people, providing an open space where human and computational intelligence can mingle-a new frontier for distributed agent systems. However, participants typically have limited autonomy to define and shape the machines they are part of. In this paper, we envision a future where individuals are able to develop their own Social Machines, enabling them to interact in a trustworthy, decentralized way. To make this possible, development methods and tools must see their barriers-to-entry dramatically lowered. People should be able to specify the agent roles and inte-raction patterns in an intuitive, visual way, analyse and test their designs and deploy them as easy to use systems. We argue that this is a challenging but realistic goal, which should be tackled by navigating the trade-off between the accessibility of the design methods -primarily the modelling formalisms- And their expressive power. We support our arguments by drawing ideas from different research areas including electronic institutions, agent-based simulation, process modelling, formal verification, and model-driven engineering. © 2018 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.