Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Personalized Federated Learning with Feature Alignment and Classifier Collaboration

About

Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients. One such approach in deep neural networks based tasks is employing a shared feature representation and learning a customized classifier head for each client. However, previous works do not utilize the global knowledge during local representation learning and also neglect the fine-grained collaboration between local classifier heads, which limit the model generalization ability. In this work, we conduct explicit local-global feature alignment by leveraging global semantic knowledge for learning a better representation. Moreover, we quantify the benefit of classifier combination for each client as a function of the combining weights and derive an optimization problem for estimating optimal weights. Finally, extensive evaluation results on benchmark datasets with various heterogeneous data scenarios demonstrate the effectiveness of our proposed method. Code is available at https://github.com/JianXu95/FedPAC

Jian Xu, Xinyi Tong, Shao-Lun Huang• 2023

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy8.42
3518
Image ClassificationCIFAR-10 (test)
Accuracy48.08
3381
Image ClassificationCIFAR-10
Accuracy77.2
507
Image ClassificationFashionMNIST (test)
Accuracy84.42
218
Image ClassificationMiniImagenet
Accuracy37.72
206
Image ClassificationCINIC-10 (test)
Accuracy34.34
177
Image ClassificationOfficeHome
Average Accuracy66.61
131
Image ClassificationCIFAR-10-C
Accuracy69.5
127
Image ClassificationCIFAR10 0.1-Dirichlet (test)
Generalized Accuracy (Accg)50.1
38
Image ClassificationFashion-MNIST under sudden drift and Dir(0.1) 1.0 (test)
Accuracy (Generalized)79.96
28
Showing 10 of 26 rows

Other info

Follow for update