Sep 2026· Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence· 0 citations· 63 references
TL;DR
This work revisits hypernetworks and proposes a model heterogeneous personalized federated learning framework, MH-pFedHN, which quantifies clients with different architectures using customized embedding vectors and then generates client-specific model parameters through a server-side hypernetwork.
Abstract
Recent personalized federated learning research focuses on heterogeneous models across clients. However, existing methods often rely on external data, model decoupling, and partial learning, which makes them sensitive to settings. In contrast, we revisit hypernetworks and leverage their strong generalization ability to propose the first practical method for personalized federated learning. We first propose a model heterogeneous personalized federated learning framework based on hypernetworks, MH-pFedHN, which quantifies clients with different architectures using customized embedding vectors and then generates client-specific model parameters through a server-side hypernetwork. Besides the shared feature extractor, our hypernetwork consists of multiple heads, where clients with similar numbers of parameters are assigned the same number of customized embedding vectors and consequently share the same head. This design enables knowledge sharing across different architectures and reduces the computation of parameter generation. To further enhance the hypernetwork’s learning and generalization, we propose MH-pFedHNGD, which introduces a lightweight yet effective plug-in global model. Our framework requires no external data and does not disclose client model architectures, thereby effectively ensuring security and demonstrating great potential. Experiments across various models and tasks demonstrate that our approach outperforms standard baselines and exhibits strong generalization performance. Our code is available at https://github.com/DangDang1895/MH-pFL
This work proposes SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model that mitigates negative transfer and enhances robustness in heterogeneous settings.
V. ArunKumarA, Sunil Gupta, N. Dang et al.· 0 citations
The Federated Parallel Scaling (FPS) algorithm is proposed, which jointly trains multiple sampled subnetworks in parallel with self-distillation so that larger sampled subnetworks can supervise smaller ones during local updates.
Jia-Xin Zhang, Xing-Wei Wang, Bo Yi et al.· 0 citations
A novel framework is introduced, FedGPA, which integrates the global model, clustered models, individual optimal models, and individual local models through an aggregation mechanism leveraging the hierarchical structure of deep neural networks, and incorporates an adaptive weight matrix that dynamically adjusts feature...
Split Federated Learning (SFL) has emerged as a pivotal paradigm for privacy-preserving distributed training on resource-constrained edge devices by partitioning neural networks between clients and a server. A critical design choice in SFL is the split layer, which determines the computation distribution and the semant...
Ai-Jing Li, Ya-Wen Li, Guan-Hua Ye et al.· Proceedings of the Thirty-Fi...· 0 citations
It is demonstrated that prediction-space meta-learning constitutes a practical alternative for federated aggregation without requiring shared parameter initialization, and among the different forms of heterogeneity in federated learning, this work focuses on statistical and model heterogeneity.