Personalized Semantics Excitation for Federated Image Classification
Federated learning casts a light on the collaboration of distributed local clients with privacy protected to attain a more generic global model. However, significant distribution shift in input/label space across different clients makes it challenging to well generalize to all clients, which motivates personalized federated learning (PFL). Existing PFL methods typically customize the local model by fine-tuning with limited local supervision and the global model regularizer, which secures local specificity but risks ruining the global discriminative knowledge. In this paper, we propose a novel Personalized Semantics Excitation (PSE) mechanism to breakthrough this limitation by exciting and fusing personalized semantics from the global model during local model customization. Specifically, PSE explores channel-wise gradient differentiation across global and local models to identify important low-level semantics mostly from convolutional layers which are embedded into the client-specific training. In addition, PSE deploys the collaboration of global and local models to enrich high-level feature representations and facilitate the robustness of client classifier through a cross-model attention module. Extensive experiments and analysis on various image classification benchmarks demonstrate the effectiveness and advantage of our method over the state-of-the-art PFL methods.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationFederated Learningimage-classificationImage ClassificationPersonalized Federated LearningSpecificitySimilar Papers 제목 키워드 기반
Personalized Quantum Federated Learning for Privacy Image Classification
Quantum federated learning has brought about the improvement of privacy image classification, while the lack of personality of the client model may contribute to the suboptimal of quantum federated learning. A personaliz…
ClassificationFederated Learningimage-classificationImage Classification+1Tackling Data Heterogeneity in Federated Learning with Class Prototypes
Data heterogeneity across clients in federated learning (FL) settings is a widely acknowledged challenge. In response, personalized federated learning (PFL) emerged as a framework to curate local models for clients' task…
Federated LearningPersonalized Federated LearningLearn What You Need in Personalized Federated Learning
Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parameters or predefined partial parameters in…
Federated Learningimage-classificationImage ClassificationPersonalized Federated LearningFederated Learning of Shareable Bases for Personalization-Friendly Image Classification
Personalized federated learning (PFL) aims to harness the collective wisdom of clients' data while building personalized models tailored to individual clients' data distributions. Existing works offer personalization pri…
Federated Learningimage-classificationImage ClassificationPersonalized Federated LearningFCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoring
Limited training data and severe class imbalance impose significant challenges to developing clinically robust deep learning models. Federated learning (FL) addresses the former by enabling different medical clients to c…
Federated Learningimage-classificationImage ClassificationLesion Classification+2