mlsanityData to 14 Oct 2026

Federated Graph Semantic and Structural Learning

arXiv 2406.18937 ↗First posted 27 Jun 2024cs.LG cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

Federated graph learning collaboratively learns a global graph neural network with distributed graphs, where the non-independent and identically distributed property is one of the major challenges. Most relative arts focus on traditional distributed tasks like images and voices, incapable of graph structures. This paper firstly reveals that local client distortion is brought by both node-level semantics and graph-level structure. First, for node-level semantics, we find that contrasting nodes from distinct classes is beneficial to provide a well-performing discrimination. We pull the local node towards the global node of the same class and push it away from the global node of different classes. Second, we postulate that a well-structural graph neural network possesses similarity for neighbors due to the inherent adjacency relationships. However, aligning each node with adjacent nodes hinders discrimination due to the potential class inconsistency. We transform the adjacency relationships into the similarity distribution and leverage the global model to distill the relation knowledge into the local model, which preserves the structural information and discriminability of the local model. Empirical results on three graph datasets manifest the superiority of the proposed method over its counterparts.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 41 of its 69 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

41 of 69 references.

References · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  6. 2017Graph Attention Networkscited by 8,923
  7. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  9. 2017Inductive Representation Learning on Large Graphscited by 6,320
  10. 2019Advances and Open Problems in Federated Learningcited by 3,046
  11. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  12. 2020Supervised Contrastive Learningcited by 2,829
29 more
  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  2. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  3. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  4. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2020Adaptive Federated Optimizationcited by 1,046
  8. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  9. 2019Relational Knowledge Distillationcited by 889
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  12. 2020Deep Graph Contrastive Representation Learningcited by 539
  13. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
  14. 2021Graph Self-Supervised Learning: A Surveycited by 289
  15. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 232
  16. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  17. 2021SEED: Self-supervised Distillation For Visual Representationcited by 134
  18. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  19. 2021Federated Graph Classification over Non-IID Graphscited by 114
  20. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  21. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  22. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  23. 2020CompRess: Self-Supervised Learning by Compressing Representationscited by 62
  24. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  25. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  26. 2022Personalized Subgraph Federated Learningcited by 54
  27. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  28. 2020ISD: Self-Supervised Learning by Iterative Similarity Distillationcited by 33
  29. 2020Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networkscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 13; 2026: 7.

30 papers.

Sort:

By area:

  1. 2024LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steeringcited by 51
  2. 2024OpenFGL: A Comprehensive Benchmark for Federated Graph Learningcited by 16
  3. 2024Federated Graph Learning with Structure Proxy Alignmentcited by 14
  4. 2025Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglementcited by 14
  5. 2024Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graphcited by 10
  6. 2024GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruningcited by 8
  7. 2025FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modelingcited by 8
  8. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  9. 2025A Comprehensive Data-centric Overview of Federated Graph Learningcited by 7
  10. 2026FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detectioncited by 6
  11. 2024Federated Continual Graph Learningcited by 5
  12. 2025Homophily Heterogeneity Matters in Graph Federated Learning: A Spectrum Sharing and Complementing Perspectivecited by 4
18 more
  1. 2024Federated Graph Learning with Graphless Clientscited by 3
  2. 2024Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learningcited by 3
  3. 2025Data-centric Federated Graph Learning with Large Language Modelscited by 3
  4. 2025Rethinking Client-oriented Federated Graph Learningcited by 2
  5. 2026Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approachcited by 2
  6. 2024DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanismcited by 1
  7. 2025Federated Prototype Graph Learningcited by 1
  8. 2025Towards Unbiased Federated Graph Learning: Label and Topology Perspectivescited by 1
  9. 2025GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generationcited by 1
  10. 2026Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Frameworkcited by 1
  11. 2026Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneitycited by 1
  12. 2024Enhancing Federated Graph Learning via Adaptive Fusion of Structural and Node Characteristicscited by 0
  13. 2025Knowledge-Driven Federated Graph Learning on Model Heterogeneitycited by 0
  14. 2025Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysiscited by 0
  15. 2025Sharpness-aware Federated Graph Learningcited by 0
  16. 2026Beyond Rigid Alignment: Graph Federated Learning via Dual Manifold Calibrationcited by 0
  17. 2026Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learningcited by 0
  18. 2026Towards Adaptive Federated Graph Clustering: A Global Community-aware Contrastive Learning-based Approachcited by 0