Personalized federated few-shot node classification  

作　　者：Yunfeng ZHAO Xintong HE Guoxian YU Jun WANG Yongqing ZHENG Carlotta DOMENICONI 

机构地区：[1]School of Software,Shandong University,Jinan 250101,China [2]Joint SDU-NTU Centre for Artificial Intelligence Research,Shandong University,Jinan 250101,China [3]Department of Mathematics,National University of Singapore,Singapore 119077,Singapore [4]Department of Computer Science,George Mason University,Virginia 22030,USA

出　　处：《Science China(Information Sciences)》2025年第1期201-215,共15页中国科学(信息科学)(英文版)

基　　金：partially supported by National Key Research and Development Program of China (Grant No. 2023YFF0725500);National Natural Science Foundation of China (Grant No. 62031003);Taishan Scholar Project Special Funding;the Xiaomi Young Talents Program

摘　　要：Personalized federated learning(PFL)aims to train customized models for individual clients in a decentralized setting,with the account of non-independent and identically distributed data across clients.However,most PFL methods adopt uniform classification layers for diverse clients and give rise to error-prone predictions,due to the task heterogeneity notably prominent in decentralized graph data scenarios.Although some PFL solutions setup client-specific classification layers for each client and optimize them only locally,they are corrupted with limited local training data.We propose an innovative solution called federated parameter decoupling and node augmentation(FedPANO)to address these problems and to achieve personalized federated few-shot node classification,which is a prevalent and challenging but unexplored topic.Specifically,FedPANO first separates the local model into the GNN and classifier to handle unique client-specific task variations.The GNN is trained through federated learning to capture shared knowledge of graph nodes across clients,while the classifier is custom-designed and trained individually for each client.Additionally,a generic classifier shared among clients is adopted to encourage the GNN’s grasp of shared information.Then FedPANO further proposes the node generator along with its local and collaborative training strategies to deal with the node scarcity of clients.Extensive experimental results on benchmark datasets confirm that FedPANO outperforms eight competitive baselines across different settings.

关 键 词：personalized federated learning few-shot learning node classification task heterogeneity parameter decoupling node augmentation 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] O157.5[自动化与计算机技术—控制科学与工程]