3rD Workshop on Advancements in Federated Learning

AI-based systems, especially those based on machine learning technologies, have become central in modern societies. In the meanwhile, users and legislators are becoming aware of privacy issues. Users are increasingly reluctant to share their sensitive information, and new laws have been enacted to regulate how private data is handled (e.g., the GDPR).

Federated Learning (FL) has been proposed to develop better AI systems without compromising users’ privacy and the legitimate interests of private companies. Although still in its infancy, FL has already shown significant theoretical and practical results making FL one of the hottest topics in the machine learning community.

Given the considerable potential in overcoming the challenges of protecting users’ privacy while making the most of available data, we propose WAFL (Workshop on Advancements in Federated Learning Technologies) at ECML-PKDD 2025.

This workshop aims to focus the attention of the ECML-PKDD research community on addressing the open questions and challenges in this thriving research area. Given the broad range of competencies in the ECML-PKDD community, the workshop will welcome foundational contributions and contributions expanding the scope of these techniques, such as improvements in the interpretability and fairness of the learned models.

WORKSHOP SCHEDULE (Tentative)

Opening

Speakers: Mirko Polato, Prof. Roberto Esposito (University of Torino)

Keynote

Speaker: Lydia Y. Chen (University of Neuchatel and Delft University of Technology). TO BE DEFINED

Technical Presentations

Coffee Break

Keynote 

Speaker: Michael Kamp (Ruhr-University Bochum). TO BE DEFINED

Technical Presentations

Closing

TOPICS AND THEMES

The WAFL workshop will be centered on the theme of improving and studying the Federated Learning setting. It will welcome applicative and theoretical contributions as well as contributions about specific settings and benchmarking tools. 

The topics include (but are not limited to):

• Algorithmic and theoretical advances in FL

• Federated Learning with non-iid data distributions

• Security and privacy of FL systems (e.g., differential privacy, adversarial attacks, poisoning attacks, inference attacks, data anonymization, model distillation, secure multi-party computation ...)

• Other non-functional properties of FL (e.g., fairness, interpretability/explainability, personalization ...)

• FL variants and Decentralized Federated Learning (e.g., vertical FL, split-learning, gossip learning, ...)

• Applications of FL (e.g., FL for healthcare, FL on edge devices, advertising, social network, blockchain, web search ...)

• Tools and resources (e.g., benchmark datasets, software libraries, ...)

SUBMISSION GUIDELINES