Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Fair Graph Federated Learning via Incentive Mechanisms (2312.13306v1)

Published 20 Dec 2023 in cs.LG, cs.AI, cs.CR, and cs.SI

Abstract: Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory incentives. This paper is the first endeavor to address this issue by studying the incentive mechanism for graph federated learning. We identify a unique phenomenon in graph federated learning: the presence of agents posing potential harm to the federation and agents contributing with delays. This stands in contrast to previous FL incentive mechanisms that assume all agents contribute positively and in a timely manner. In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff. To achieve this, we first introduce an agent valuation function aimed at quantifying agent contributions through the introduction of two criteria: gradient alignment and graph diversity. Moreover, due to the high heterogeneity in graph federated learning, striking a balance between accuracy and fairness becomes particularly crucial. We introduce motif prototypes to enhance accuracy, communicated between the server and agents, enhancing global model aggregation and aiding agents in local model optimization. Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Protein function prediction via graph kernels. Bioinformatics, 21 Suppl 1: i47–56.
  2. FAIR: Quality-Aware Federated Learning with Precise User Incentive and Model Aggregation. In IEEE Conference on Computer Communications.
  3. Distinguishing enzyme structures from non-enzymes without alignments. Journal of molecular biology, 330(4): 771–783.
  4. Fairfed: Enabling group fairness in federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence.
  5. Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries. In Proceedings of the International Conference on Neural Information Processing Systems.
  6. FIFL: A Fair Incentive Mechanism for Federated Learning. In Proceedings of the International Conference on Parallel Processing.
  7. Profit sharing and efficiency in utility games. In Annual European Symposium on Algorithms.
  8. Privacy, accuracy, and model fairness trade-offs in federated learning. Computers & Security, 122: 102907.
  9. Dynamic Activation of Clients and Parameters for Federated Learning over Heterogeneous Graphs. In International Conference on Data Engineering.
  10. Inductive Representation Learning on Large Graphs. In Proceedings of the International Conference on Neural Information Processing Systems.
  11. Fedgraphnn: A federated learning system and benchmark for graph neural networks. arXiv preprint arXiv:2104.07145.
  12. Spreadgnn: Serverless multi-task federated learning for graph neural networks. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society.
  13. Towards efficient data valuation based on the shapley value. In International Conference on Artificial Intelligence and Statistics.
  14. Scaffold: Stochastic controlled averaging for federated learning. In International Conference on Machine Learning.
  15. Federated Optimization in Heterogeneous Networks. In Proceedings of Machine Learning and Systems.
  16. Collaborative fairness in federated learning. Federated Learning: Privacy and Incentive, 189–204.
  17. Communication-efficient learning of deep networks from decentralized data. In International Conference on Artificial intelligence and statistics.
  18. Cross-node federated graph neural network for spatio-temporal data modeling. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
  19. Prototype Guided Federated Learning of Visual Feature Representations. arXiv preprint arXiv:2105.08982.
  20. Network motifs: simple building blocks of complex networks. Science, 298(5594): 824–827.
  21. TUDataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663.
  22. CogBoost: Boosting for Fast Cost-Sensitive Graph Classification. IEEE Transactions on Knowledge and Data Engineering, 27: 2933–2946.
  23. Shapley, L. S. 1997. A value for n-person games. Classics in game theory, 69.
  24. Profit allocation for federated learning. In IEEE International Conference on Big Data.
  25. Federated Learning on Non-IID Graphs via Structural Knowledge Sharing. In Proceedings of the AAAI Conference on Artificial Intelligence.
  26. Fedproto: Federated prototype learning across heterogeneous clients. In Proceedings of the AAAI Conference on Artificial Intelligence.
  27. Graphfl: A federated learning framework for semi-supervised node classification on graphs. In IEEE International Conference on Data Mining.
  28. A principled approach to data valuation for federated learning. Federated Learning: Privacy and Incentive, 153–167.
  29. Fedgnn: Federated graph neural network for privacy-preserving recommendation. arXiv preprint arXiv:2102.04925.
  30. Federated graph classification over non-iid graphs. In Proceedings of the International Conference on Neural Information Processing Systems.
  31. Federated node classification over graphs with latent link-type heterogeneity. In Proceedings of the ACM Web Conference.
  32. Better with Less: A Data-Centric Prespective on Pre-Training Graph Neural Networks. In Proceedings of the International Conference on Neural Information Processing Systems.
  33. A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning. ICML Workshop on Federated Learning for User Privacy and Data Confidentiality.
  34. Gradient driven rewards to guarantee fairness in collaborative machine learning. In Proceedings of the International Conference on Neural Information Processing Systems.
  35. Deep graph kernels. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
  36. On designing data quality-aware truth estimation and surplus sharing method for mobile crowdsensing. IEEE Journal on Selected Areas in Communications, 35(4): 832–847.
  37. A Fairness-aware Incentive Scheme for Federated Learning. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society.
  38. Molecular representation learning via heterogeneous motif graph neural networks. In International Conference on Machine Learning.
  39. On Explainability of Graph Neural Networks via Subgraph Explorations. In International Conference on Machine Learning.
  40. A learning-based incentive mechanism for federated learning. IEEE Internet of Things Journal, 7(7): 6360–6368.
  41. Big data analytics by crowdlearning: Architecture and mechanism design. IEEE Network, 34(3): 143–147.
  42. FASTGNN: A Topological Information Protected Federated Learning Approach for Traffic Speed Forecasting. IEEE Transactions on Industrial Informatics, 17: 8464–8474.
  43. Subgraph federated learning with missing neighbor generation. In Proceedings of the International Conference on Neural Information Processing Systems.
  44. Motif-based graph self-supervised learning for molecular property prediction. In Proceedings of the International Conference on Neural Information Processing Systems.
  45. Federated learning with non-iid data. arXiv preprint arXiv:1806.00582.
  46. ASFGNN: Automated separated-federated graph neural network. Peer-to-Peer Networking and Applications, 14(3): 1692–1704.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (8)
  1. Chenglu Pan (2 papers)
  2. Jiarong Xu (24 papers)
  3. Yue Yu (343 papers)
  4. Ziqi Yang (26 papers)
  5. Qingbiao Wu (6 papers)
  6. Chunping Wang (23 papers)
  7. Lei Chen (485 papers)
  8. Yang Yang (884 papers)
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now