FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks
Not on the map. Why?
Abstract (arXiv)
Personalized Federated Learning (PFL) aims to address the statistical heterogeneity of data across clients by learning the personalized model for each client. Among various PFL approaches, the personalized aggregation-based approach conducts parameter aggregation in the server-side aggregation phase to generate personalized models, and focuses on learning appropriate collaborative relationships among clients for aggregation. However, the collaborative relationships vary in different scenarios and even at different stages of the FL process. To this end, we propose Personalized Federated Learning with Attentive Graph HyperNetworks (FedAGHN), which employs Attentive Graph HyperNetworks (AGHNs) to dynamically capture fine-grained collaborative relationships and generate client-specific personalized initial models. Specifically, AGHNs empower graphs to explicitly model the client-specific collaborative relationships, construct collaboration graphs, and introduce tunable attentive mechanism to derive the collaboration weights, so that the personalized initial models can be obtained by aggregating parameters over the collaboration graphs. Extensive experiments can demonstrate the superiority of FedAGHN. Moreover, a series of visualizations are presented to explore the effectiveness of collaboration graphs learned by FedAGHN.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 24 Jan 2025.
Builds on
27 of 49 references.
References · 27
- 2017Graph Attention Networkscited by 8,854
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2020Personalized Federated Learning with Moreau Envelopescited by 612
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2021Towards Personalized Federated Learningcited by 462
- 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
- 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
- 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
15 more
- 2021Personalized Federated Learning using Hypernetworkscited by 210
- 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
- 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 121
- 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
- 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 95
- 2020Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computingcited by 52
- 2022FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learningcited by 43
- 2023FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policycited by 36
- 2021Layer-wise Adaptive Model Aggregation for Scalable Federated Learningcited by 35
- 2022Personalized Federated Learning With Graphcited by 29
- 2021A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularizationcited by 27
- 2022Federated Learning with Heterogeneous Architectures using Graph HyperNetworkscited by 17
- 2022Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applicationscited by 14
- 2024Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphscited by 5
Built on by
Citing papers per year: 2025: 1.
1 paper.