Your Data, My Model: Learning Who Really Helps in Federated Learning
Not on the map. Why?
Abstract (arXiv)
Many important machine learning applications involve networks of devices-such as wearables or smartphones-that generate local data and train personalized models. A key challenge is determining which peers are most beneficial for collaboration. We propose a simple and privacy-preserving method to select relevant collaborators by evaluating how much a model improves after a single gradient step using another devices data-without sharing raw data. This method naturally extends to non-parametric models by replacing the gradient step with a non-parametric generalization. Our approach enables model-agnostic, data-driven peer selection for personalized federated learning (PersFL).
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 27 references that are in the map. First posted on arXiv 3 Sep 2024.
Builds on
11 of 27 references.
References · 11
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2017Federated Multi-Task Learningcited by 669
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2015Network Lasso: Clustering and Optimization in Large Graphscited by 42
- 2023Personalized Federated Learning under Mixture of Distributionscited by 37
- 2023Confidence-aware Personalized Federated Learning via Variational Expectation Maximizationcited by 17
- 2023Provably Personalized and Robust Federated Learningcited by 11
- 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
- 2021Clustered Federated Learning via Generalized Total Variation Minimizationcited by 7
- 2021Low-Regret Active learningcited by 3
Built on by
Not cited yet.