Personalized One-shot Federated Graph Learning for Heterogeneous Clients
Not on the map. Why?
Abstract (arXiv)
Federated Graph Learning (FGL) has emerged as a promising paradigm for breaking data silos among distributed private graphs. In practical scenarios involving heterogeneous distributed graph data, personalized Federated Graph Learning (pFGL) aims to enhance model utility by training personalized models tailored to client needs. However, existing pFGL methods often require numerous communication rounds under heterogeneous graphs, leading to significant communication overhead and security concerns. While One-shot Federated Learning (OFL) enables collaboration in a single round, existing OFL methods are designed for image-centric tasks and are ineffective for graph data, leaving a critical gap in the field. Additionally, personalized models derived from existing methods suffer from bias, failing to effectively generalize to the minority. To address these challenges, we propose the first One-shot personalized Federated Graph Learning method (O-pFGL) for node classification, compatible with Secure Aggregation protocols for privacy preservation. Specifically, for effective graph learning in one communication round, our method estimates and aggregates class-wise feature distribution statistics to construct a global surrogate graph on the server, facilitating the training of a global graph model. To mitigate bias, we introduce a two-stage personalized training approach that adaptively balances local personal information and global insights from the surrogate graph, improving both personalization and generalization. Extensive experiments on 14 diverse real-world graph datasets demonstrate that our method significantly outperforms state-of-the-art baselines across various settings.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 65 references that are in the map. First posted on arXiv 18 Nov 2024.
Builds on
39 of 65 references.
References · 39
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
27 more
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
- 2019Label Propagation for Deep Semi-supervised Learningcited by 289
- 2020SIGN: Scalable Inception Graph Neural Networkscited by 284
- 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
- 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
- 2019One-Shot Federated Learningcited by 125
- 2021Federated Graph Classification over Non-IID Graphscited by 114
- 2020Distilled One-Shot Federated Learningcited by 109
- 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
- 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
- 2020GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphscited by 64
- 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
- 2022Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environmentscited by 49
- 2020FedE: Embedding Knowledge Graphs in Federated Settingcited by 46
- 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
- 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
- 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boostingcited by 27
- 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learningcited by 27
- 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
- 2019Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Modelscited by 19
- 2023Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendationcited by 19
- 2023GPFedRec: Graph-guided Personalization for Federated Recommendationcited by 18
- 2024FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Modelscited by 17
- 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
- 2024Federated Graph Learning with Structure Proxy Alignmentcited by 14
- 2023Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devicescited by 6
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.