Proposers
Dr. Xilu Wang, Prof. Chaoli Sun and Prof. Ferrante Neri
Workshop Code
Please use the following code when submitting your paper to this Workshop: W6-FEDE
Scope and Aims
Optimization and machine learning problems are pervasive in economic, scientific, and engineering applications. While significant advancements have been made in both fields, traditional approaches often assume centralized resources and data. However, this assumption is increasingly violated with the growing storage of personal data and computational power of edge devices. Federated learning has emerged as a popular paradigm that leverages distributed data without leaking sensitive information by aggregating local models trained on different devices using local data. Similarly, federated optimization techniques solve complex problems using distributed data and computational resources.
Both federated learning and data-driven optimization raise critical concerns about data security, privacy protection, and fairness. Outcomes can be affected by data or algorithmic biases, potentially generating unfair results. When these outcomes correlate with real-world rewards (e.g., financial gains or resource allocation), participants may hesitate to collaborate if they perceive disproportionately smaller benefits. This underscores the importance of developing privacy-preserving and fairness-aware techniques spanning both optimization and learning domains.
This workshop aims to bring together researchers and practitioners to discuss recent advances, share insights, and identify future research directions in fairness-aware federated optimization and learning. It provides a platform for interdisciplinary dialogue between the optimization and machine learning communities.
Content and Objectives
The workshop will feature presentations of peer-reviewed papers and invited talks from leading experts. Topics include but are not limited to:
Security-Focused
- Secure federated optimization and learning
- Secure multi-party computation for optimization
- Byzantine-robust distributed optimization
Fairness-Focused
- Fairness-aware federated optimization and learning
- Fairness-aware multi-objective machine learning
- Fairness-aware Bayesian optimization and data-driven optimization
- Fairness-aware multi-objective and many-objective optimization
- Fair resource allocation in distributed systems
Privacy-Focused
- Privacy-preserving Bayesian optimization and distributed optimization
- Privacy-preserving evolutionary algorithm and data-driven optimization
- Privacy-utility-fairness trade-off analysis and Pareto optimization
Objectives:
- Foster collaboration between optimization and machine learning communities
- Identify emerging research challenges in fairness and privacy for federated systems
- Promote reproducible research through shared benchmarks and datasets
- Facilitate knowledge transfer between academia and industry