Federated Prototype Graph Learning
Not on the map. Why?
Abstract (arXiv)
In recent years, Federated Graph Learning (FGL) has gained significant attention for its distributed training capabilities in graph-based machine intelligence applications, mitigating data silos while offering a new perspective for privacy-preserve large-scale graph learning. However, multi-level FGL heterogeneity presents various client-server collaboration challenges: (1) Model-level: The variation in clients for expected performance and scalability necessitates the deployment of heterogeneous models. Unfortunately, most FGL methods rigidly demand identical client models due to the direct model weight aggregation on the server. (2) Data-level: The intricate nature of graphs, marked by the entanglement of node profiles and topology, poses an optimization dilemma. This implies that models obtained by federated training struggle to achieve superior performance. (3) Communication-level: Some FGL methods attempt to increase message sharing among clients or between clients and the server to improve training, which inevitably leads to high communication costs. In this paper, we propose FedPG as a general prototype-guided optimization method for the above multi-level FGL heterogeneity. Specifically, on the client side, we integrate multi-level topology-aware prototypes to capture local graph semantics. Subsequently, on the server side, leveraging the uploaded prototypes, we employ topology-guided contrastive learning and personalized technology to tailor global prototypes for each client, broadcasting them to improve local training. Experiments demonstrate that FedPG outperforms SOTA baselines by an average of 3.57% in accuracy while reducing communication costs by 168x.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 54 of its 80 references that are in the map. First posted on arXiv 13 Apr 2025.
Builds on
54 of 80 references.
References · 54
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
- 2020Simple and Deep Graph Convolutional Networkscited by 860
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
- 2021Model-Contrastive Federated Learningcited by 766
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
38 more
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2020SIGN: Scalable Inception Graph Neural Networkscited by 284
- 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
- 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
- 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 195
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
- 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
- 2021Federated Graph Classification over Non-IID Graphscited by 114
- 2020Line Graph Neural Networks for Link Predictioncited by 89
- 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
- 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
- 2019Hierarchical Graph Pooling with Structure Learningcited by 81
- 2023LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendationcited by 72
- 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 71
- 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 67
- 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
- 2022Personalized Subgraph Federated Learningcited by 54
- 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
- 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
- 2022PaSca: a Graph Neural Architecture Search System under the Scalable Paradigmcited by 37
- 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
- 2022DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generationcited by 33
- 2024Federated Graph Semantic and Structural Learningcited by 30
- 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learningcited by 27
- 2022Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selectioncited by 26
- 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
- 2021A New Perspective on the Effects of Spectrum in Graph Neural Networkscited by 24
- 2022FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networkscited by 24
- 2022Node-oriented Spectral Filtering for Graph Neural Networkscited by 17
- 2023Vertical Federated Graph Neural Network for Recommender Systemcited by 17
- 2024Rethinking Node-wise Propagation for Large-scale Graph Learningcited by 16
- 2024Deep Efficient Private Neighbor Generation for Subgraph Federated Learningcited by 14
- 2021Adaptive Neural Message Passing for Inductive Learning on Hypergraphscited by 10
- 2023HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learningcited by 8
50 most cited of 54 All 54 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.