posted by organizer: gcfac || 1216 views || tracked by 3 users: [display]

IEEE CIDM/SSCI - RLFCA 2017 : Representation learning for transfer and collaborative approaches (Special session in IEEE CIDM/SSCI 2017)


When Nov 27, 2017 - Dec 1, 2017
Where Honolulu, Hawaii, USA
Submission Deadline Jul 16, 2017
Notification Due Aug 27, 2017
Final Version Due Sep 24, 2017

Call For Papers

Call for Papers in Special Session
Representation learning for transfer and collaborative approaches

IEEE Symposium on Computational Intelligence and Data Mining (CIDM)
IEEE Symposium Series of Computational Intelligence (SSCI 2017)
Honolulu, Hawaii, Nov 27 – Dec 1, 2017.

Papers due July 16

Submission :
Select "CIDM6" as Main research topic

Data Clustering is a fundamental task in the process of knowledge extraction from databases that aims to discover the intrinsic structures in a set of objects by forming clusters that share similar features. Over the past two decades, these tasks have become even more challenging when the available data sets became more complex with the introduction of multi-view data sets, distributed data, data streams and data set having different scales of structures of interest (e.g. hierarchical clusters). Because of this increased complexity in an already hard problem, new approaches are needed.

Within this context, the purpose of our session is to bring together researchers working on unsupervised frameworks learning involving a decomposition of the clustering task into several sub-problems. The decomposition can involve algorithms working on different subsets of a multi-view or a distributed data set, searching for different scales of interested in the same data to find hierarchical structures, analyzing in parallel different time periods of a data stream, etc… These approaches are a recent area of research with a large number of applications to tackle difficult problems, such as clustering of distributed data, multi-expert clustering, multi-scale clustering analysis or multi-view clustering. Most of these frameworks can be regrouped under the umbrella of transfer and collaborative learning, the aim of which is to reveal the underlying structure of the data by sharing information between algorithms working on different sub-problems.

Topics of interest include, but are not limited to the following:
- Collaborative clustering
- Collaborative learning
- Cooperative learning
- Multi-view learning
- Multi-task learning
- Transfers learning
- Representation learning
- Modular approaches
- Distributed data
- Task decomposition

Contact Session Co-Chairs:
- Guénaël Cabanes: Institut Galilée, University Paris 13, France (contact:
- Younès Bennani: Institut Galilée, University Paris 13, France
- Nistor Grozavu: Institut Galilée, University Paris 13, France
- Basarab Matei: Institut Galilée, University Paris 13, France

Related Resources

POLTRANCOV 2021   CfP: Policy Transfer and Learning in the Context of COVID-19 Pandemic
IEEE TETC-ETTRML 2021   Special Section on “To Be Safe and Dependable in the Era of Artificial Intelligence: Emerging Techniques for Trusted and Reliable Machine Learning”
KR 2021   18th International Conference on Principles of Knowledge Representation and Reasoning
RepL4NLP 2021   Call for Papers - Workshop on Representation Learning for NLP (RepL4NLP) at ACL 2021
FTL-IJCAI 2021   International Workshop on Federated and Transfer Learning for Data Sparsity and Confidentiality in Conjunction with IJCAI 2021
AIKE 2021   IEEE Artificial Intelligence & Knowledge Engineering 2021
HoWCoM 2021   1st Hands-on Workshop on Collaborative Modeling
ICADCML 2022   3rd International Conference on Advances in Distributed Computing and Machine Learning - 2022
IEEE WCCI 2022   IEEE World Congress on Computational Intelligence
EAI CollaborateCom 2021   17th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing (Springer, Scopus, ISI, Ei, more)