Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data
Abstract
In Federated Learning, heterogeneity in client data distributions often means that a single global model does not have the best performance for individual clients. Consider for example training a next-word prediction model for keyboards: user-specific language patterns due to demographics (dialect, age, etc.), language proficiency, and writing style result in a highly non-IID dataset across clients. Other examples are medical images taken with different machines, or driving data from different vehicle types. To address this, we propose a simple yet effective personalized federated learning framework (pFedLIA) that utilizes a computationally efficient influence approximation, called `Lazy Influence', to cluster clients in a distributed manner before model aggregation. Within each cluster, data owners collaborate to jointly train a model that captures the specific data patterns of the clients. Our method has been shown to successfully recover the global model's performance drop due to the non-IID-ness in various synthetic and real-world settings, specifically a next-word prediction task on the Nordic languages as well as several benchmark tasks. It matches the performance of a hypothetical Oracle clustering, and significantly improves on existing baselines, e.g., an improvement of 17% on CIFAR100.
Cite
@article{arxiv.2505.02540,
title = {Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data},
author = {Ljubomir Rokvic and Panayiotis Danassis and Boi Faltings},
journal= {arXiv preprint arXiv:2505.02540},
year = {2025}
}
Comments
Accepted at the International Joint Conference on Neural Networks (IJCNN), IEEE, 2025