Towards heterogeneous federated graph learning via structural entropy and prototype aggregation
Authors:
- Zhehao DaiZDZhehao Dai
- Guojiang ShenGSGuojiang Shen
- Haopeng YuanHYHaopeng Yuan
- Shangfei ZhengSZShangfei Zheng
- Yuyue HuYHYuyue Hu
- Jiaxin DuJDJiaxin Du
- Xiangjie KongXKXiangjie Kong
- Feng XiaFXFeng Xia
- 27 May 2025
- journal article
- Published by Elsevier in Information Sciences
- Vol. 718
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Zhejiang Province (LR21F020003, LQ24F020038)
- Pioneer and Leading Goose R&D Program of Zhejiang
- National Natural Science Foundation of China (62402442, 62072409, 62476247, 2024C01214)
This publication has 11 references indexed in Scilit:
- Auto-weighted Graph Reconstruction for efficient ensemble clusteringInformation Sciences, 2024
- Mitigating data imbalance and generating better prototypes in heterogeneous Federated Graph LearningKnowledge-Based Systems, 2024
- EGRC-Net: Embedding-Induced Graph Refinement Clustering NetworkIEEE Transactions on Image Processing, 2023
- Auto-weighted orthogonal and nonnegative graph reconstruction for multi-view clusteringInformation Sciences, 2023
- Automated Graph Neural Network Search Under Federated Learning FrameworkIEEE Transactions on Knowledge and Data Engineering, 2023
- Federated Graph Machine LearningACM SIGKDD Explorations Newsletter, 2022
- Communication-efficient federated learning via knowledge distillationNature Communications, 2022
- Generative adversarial networksCommunications of the ACM, 2020
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Structural Information and Dynamical Complexity of NetworksIEEE Transactions on Information Theory, 2016