Toward Personalized Federated Meta-Learning With Constrained Hypernetwork on Non-IID Data
- 24 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (1) , 233-246
Abstract
Personalized Federated Learning (pFL) tailors models to each client’s local data distribution in heterogeneous federated learning settings. Federated Meta-Learning (FML) is a branch of pFL that uses meta-learning to achieve fast adaptation, where clients start with a meta-model and personalize it by fine-tuning it with local data. Since a single global meta-model has limitations when the data distribution of clients varies significantly, meta-model personalization should be considered in FML. However, most benchmark pFL methods lack meta-model personalization, and usually lack meta-learning or relying on a single global meta-model. Besides, these methods can neither provide meta-model personalization nor guarantee generalization and convergence, due to the challenges in measuring the distance between the meta-model and the client model in FML. To address these issues, we combine FML with hypernetwork and propose a constrained hypernetwork-based FML framework called FMLH, which innovatively utilizes hypernetwork to capture the differences in fine-tuned models, thereby providing personalized meta-models for each client. We provide rigorous mathematical proofs illustrating how the hypernetwork affects the convergence and generalization bounds of FMLH. Experimental results demonstrate that FMLH significantly improves the generalization of the model in cross-client shifts, with the lowest decile accuracy improved by up to 18.71%. FMLH also outperforms representative pFL algorithms by up to 5.6% in terms of maximum accuracy improvement.Keywords
Funding Information
- National Natural Science Foundation of China (62471139)
- National Natural Science Foundation of China (62302203)
- Natural Science Foundation of Fujian Province (2024H6008)
- Natural Science Foundation of Fujian Province (2025J02019)
- Natural Science Foundation of Fujian Province (2025H0043)
- Natural Science Foundation of Fujian Province (2025YZ040003)
This publication has 16 references indexed in Scilit:
- Advances in Robust Federated Learning: A Survey With Heterogeneity ConsiderationsIEEE Transactions on Big Data, 2025
- A brief review of hypernetworks in deep learningArtificial Intelligence Review, 2024
- On the Efficiency of Privacy Attacks in Federated Learning2024
- FedAS: Bridging Inconsistency in Personalized Federated Learning2024
- Federated Learning With Non-IID Data: A SurveyIEEE Internet of Things Journal, 2024
- FedTP: Federated Learning by Transformer PersonalizationIEEE Transactions on Neural Networks and Learning Systems, 2023
- Personalized Federated Learning on Non-IID Data via Group-based Meta-learningACM Transactions on Knowledge Discovery From Data, 2023
- CD2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning2022
- Layer-wised Model Aggregation for Personalized Federated Learning2022
- FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health MonitoringIEEE Transactions on Mobile Computing, 2020