IJCNN’24 Special Session on Trustworthy Federated Learning in the Era of Foundation Models (FL@FM-IJCNN 2024)

Federated Learning (FL) is an emerging machine learning paradigm that allows multiple end-users to collaboratively train models without sharing their private data. Existing FL frameworks are undergoing a significant change fueled by Foundation Models (FM), which presents a unique opportunity to unlock new possibilities, challenges, and applications in AI research. FL can be a beneficial tool to address the shortage of high-quality legalized data required by FM training. Meanwhile, FM can empower existing FL systems to alleviate performance degradation problems and lead to a better balance between generalization and personalization, diversity and fidelity. A robust, trustworthy FL platform can be established by examining the interplay between FL and FM, allowing them to benefit each other mutually. Also, it is necessary to overco