Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

Wentao Yu, Sheng Wan, Shuo Chen, Bo Han, Chen Gong
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:151187-151220, 2026.

Abstract

Graph Federated Learning (GFL) enables distributed graph representation learning while preserving graph data privacy. However, it suffers from heterogeneity in node features and graph structures across clients. To address this challenge, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA). For node feature heterogeneity, FedSSA infers class-wise node distributions through a variational model, clusters clients according to the inferred distributions, and aligns local distributions with cluster-level representatives. For structural heterogeneity, FedSSA employs spectral Graph Neural Networks (GNNs) and introduces a spectral energy measure to characterize graph topology, enabling structural alignment between local and cluster-level spectral GNNs. Experiments on eleven homophilic and heterophilic graph datasets under non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods. Our code is available at https://github.com/blgpb/FedSSA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-yu26ax, title = {Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning}, author = {Yu, Wentao and Wan, Sheng and Chen, Shuo and Han, Bo and Gong, Chen}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {151187--151220}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/yu26ax/yu26ax.pdf}, url = {https://proceedings.mlr.press/v306/yu26ax.html}, abstract = {Graph Federated Learning (GFL) enables distributed graph representation learning while preserving graph data privacy. However, it suffers from heterogeneity in node features and graph structures across clients. To address this challenge, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA). For node feature heterogeneity, FedSSA infers class-wise node distributions through a variational model, clusters clients according to the inferred distributions, and aligns local distributions with cluster-level representatives. For structural heterogeneity, FedSSA employs spectral Graph Neural Networks (GNNs) and introduces a spectral energy measure to characterize graph topology, enabling structural alignment between local and cluster-level spectral GNNs. Experiments on eleven homophilic and heterophilic graph datasets under non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods. Our code is available at https://github.com/blgpb/FedSSA.} }
Endnote
%0 Conference Paper %T Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning %A Wentao Yu %A Sheng Wan %A Shuo Chen %A Bo Han %A Chen Gong %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-yu26ax %I PMLR %P 151187--151220 %U https://proceedings.mlr.press/v306/yu26ax.html %V 306 %X Graph Federated Learning (GFL) enables distributed graph representation learning while preserving graph data privacy. However, it suffers from heterogeneity in node features and graph structures across clients. To address this challenge, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA). For node feature heterogeneity, FedSSA infers class-wise node distributions through a variational model, clusters clients according to the inferred distributions, and aligns local distributions with cluster-level representatives. For structural heterogeneity, FedSSA employs spectral Graph Neural Networks (GNNs) and introduces a spectral energy measure to characterize graph topology, enabling structural alignment between local and cluster-level spectral GNNs. Experiments on eleven homophilic and heterophilic graph datasets under non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods. Our code is available at https://github.com/blgpb/FedSSA.
APA
Yu, W., Wan, S., Chen, S., Han, B. & Gong, C.. (2026). Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:151187-151220 Available from https://proceedings.mlr.press/v306/yu26ax.html.

Related Material