mlsanityData to 14 Oct 2026

Knowledge-Driven Federated Graph Learning on Model Heterogeneity

arXiv 2501.12624 ↗First posted 22 Jan 2025cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preserving data privacy. However, most existing approaches assume homogeneous client models and largely overlook the challenge of model-centric heterogeneous FGL (MHtFGL), which frequently arises in practice when organizations employ graph neural networks (GNNs) of different scales and architectures.Such architectural diversity not only undermines smooth server-side aggregation, which presupposes a unified representation space shared across clients' updates, but also further complicates the transfer and integration of structural knowledge across clients. To address this issue, we propose the Federated Graph Knowledge Collaboration (FedGKC) framework. FedGKC introduces a lightweight Copilot Model on each client to facilitate knowledge exchange while local architectures are heterogeneous across clients, and employs two complementary mechanisms: Client-side Self-Mutual Knowledge Distillation, which transfers effective knowledge between local and copilot models through bidirectional distillation with multi-view perturbation; and Server-side Knowledge-Aware Model Aggregation, which dynamically assigns aggregation weights based on knowledge provided by clients. Extensive experiments on eight benchmark datasets demonstrate that FedGKC achieves an average accuracy gain of 3.88% over baselines in MHtFGL scenarios, while maintaining excellent performance in homogeneous settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 54 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

32 of 54 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Graph Attention Networkscited by 8,923
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  10. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
20 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  2. 2015Image-based Recommendations on Styles and Substitutescited by 706
  3. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  4. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  5. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  6. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  7. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  8. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  9. 2020Distilling Knowledge from Graph Convolutional Networkscited by 129
  10. 2021Federated Graph Classification over Non-IID Graphscited by 114
  11. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  12. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  13. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  14. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  15. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  16. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  17. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  18. 2022T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillationcited by 32
  19. 2024Federated Graph Semantic and Structural Learningcited by 30
  20. 2022Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillationcited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Federated Graph Learning with Graphless Clients
  2. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning
  3. 2024FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning
  4. 2026Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach
  5. 2021Cluster-driven Graph Federated Learning over Multiple Domains
  6. 2024Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
  7. 2024Federated Knowledge Graph Unlearning via Diffusion Model
  8. 2025Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models