Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning

About

Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training. However, the distribution shift across non-IID datasets, often poses a challenge to this one-model-fits-all solution. Personalized FL aims to mitigate this issue systematically. In this work, we propose APPLE, a personalized cross-silo FL framework that adaptively learns how much each client can benefit from other clients' models. We also introduce a method to flexibly control the focus of training APPLE between global and local objectives. We empirically evaluate our method's convergence and generalization behaviors, and perform extensive experiments on two benchmark datasets and two medical imaging datasets under two non-IID settings. The results show that the proposed personalized FL framework, APPLE, achieves state-of-the-art performance compared to several other personalized FL approaches in the literature. The code is publicly available at https://github.com/ljaiverson/pFL-APPLE.

Jun Luo, Shandong Wu• 2021

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 Pathological
Mean Accuracy64.84
35
Image ClassificationCIFAR-100 Practical Heterogeneity
Accuracy52.14
9
Image ClassificationCIFAR-10 Practical Heterogeneity
Accuracy88.57
9
Image ClassificationCIFAR-10 Pathological Heterogeneity
Accuracy90.02
9
Showing 4 of 4 rows

Other info

Follow for update