← Back to papers
2022 AAAI AAAI 2022

FedSoft: Soft Clustered Federated Learning with Proximal Local Updating

Abstract

Abstract Traditionally, clustered federated learning groups clients with the same data distribution into a cluster, so that every client is uniquely associated with one data distribution and helps train a model for this distribution. We relax this hard association assumption to soft clustered federated learning, which allows every local dataset to follow a mixture of multiple source distributions. We propose FedSoft, which trains both locally personalized models and high-quality cluster models in this setting. FedSoft limits client workload by using proximal updates to require the completion of only one optimization task from a subset of clients in every communication round. We show, analytically and empirically, that FedSoft effectively exploits similarities between the source distributions to learn personalized and cluster models that perform well.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — client clustering
🐣 Hot Topic Early Bird — personalized model
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Yichen Ruan , Carlee Joe-Wong

Topics

Artificial Intelligence > Learning Paradigms > Federated Learning Machine Learning > Core Methods > Clustering Machine Learning > Learning Types > Federated Learning Machine Learning > Learning Types > Multi-Task Learning Machine Learning > Learning Paradigms > Federated Learning Machine Learning > Core Methods > Multi-Task Learning Machine Learning > Application Areas > Transfer Learning

Keywords

federated learning personalized model client clustering soft clustering clustered federated learning clustered learning proximal update model personalization proximal local update proximal updating
Download PDF

Related papers

Dynamic Spatial Propagation Network for Depth Completion 2022
FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition 2022
Memory-Guided Semantic Learning Network for Temporal Sentence Grounding 2022
AnchorFace: Boosting TAR@FAR for Practical Face Recognition 2022
Parallel and High-Fidelity Text-to-Lip Generation 2022