Federated Subgraph Learning via Global-Knowledge-Guided Node Generation

Federated graph learning (FGL) is a combination of graph representation learning and federated learning that utilizes graph neural networks (GNNs) to process complex graph-structured data while addressing data silo issues. However, during the local training of GNNs, each client only has access to a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuxuan Liu, Zhiming He, Shuang Wang, Yangyang Wang, Peichao Wang, Zhangshen Huang, Qi Sun
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769318325157888
author Yuxuan Liu
Zhiming He
Shuang Wang
Yangyang Wang
Peichao Wang
Zhangshen Huang
Qi Sun
author_facet Yuxuan Liu
Zhiming He
Shuang Wang
Yangyang Wang
Peichao Wang
Zhangshen Huang
Qi Sun
author_sort Yuxuan Liu
collection DOAJ
description Federated graph learning (FGL) is a combination of graph representation learning and federated learning that utilizes graph neural networks (GNNs) to process complex graph-structured data while addressing data silo issues. However, during the local training of GNNs, each client only has access to a subgraph, significantly deteriorating performance. To address this issue, recent solutions propose completing the subgraph with pseudo graph nodes generated by a generator trained using the local subgraph. Despite their effectiveness, such methods may introduce biases as the local pseudo graph nodes cannot accurately represent the global graph distribution. To overcome this problem, we introduce MN-FGAGN, which mitigates the impact of missing neighbor information by generating pseudo graph nodes that follow the global distribution. The main idea of our approach is to partition the generative adversarial neural network into a client-side discriminator and a server-side generator. In this way, the generator can receive supervised information from all clients and can thus generate graph nodes that contain global information. Experiments on four real-world graph datasets show that it outperforms the state-of-the-art methods.
format Article
id doaj-art-638ba76f7b2e44adb05f6a6725433ffb
institution DOAJ
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-638ba76f7b2e44adb05f6a6725433ffb2025-08-20T03:03:27ZengMDPI AGSensors1424-82202025-04-01257224010.3390/s25072240Federated Subgraph Learning via Global-Knowledge-Guided Node GenerationYuxuan Liu0Zhiming He1Shuang Wang2Yangyang Wang3Peichao Wang4Zhangshen Huang5Qi Sun6School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaHangzhou Nuowei Information Technology Company Ltd., Hangzhou 310059, ChinaSchool of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaHangzhou Nuowei Information Technology Company Ltd., Hangzhou 310059, ChinaFederated graph learning (FGL) is a combination of graph representation learning and federated learning that utilizes graph neural networks (GNNs) to process complex graph-structured data while addressing data silo issues. However, during the local training of GNNs, each client only has access to a subgraph, significantly deteriorating performance. To address this issue, recent solutions propose completing the subgraph with pseudo graph nodes generated by a generator trained using the local subgraph. Despite their effectiveness, such methods may introduce biases as the local pseudo graph nodes cannot accurately represent the global graph distribution. To overcome this problem, we introduce MN-FGAGN, which mitigates the impact of missing neighbor information by generating pseudo graph nodes that follow the global distribution. The main idea of our approach is to partition the generative adversarial neural network into a client-side discriminator and a server-side generator. In this way, the generator can receive supervised information from all clients and can thus generate graph nodes that contain global information. Experiments on four real-world graph datasets show that it outperforms the state-of-the-art methods.https://www.mdpi.com/1424-8220/25/7/2240federated learningdistributed learninggraph learningmachine learningdeep learning
spellingShingle Yuxuan Liu
Zhiming He
Shuang Wang
Yangyang Wang
Peichao Wang
Zhangshen Huang
Qi Sun
Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
Sensors
federated learning
distributed learning
graph learning
machine learning
deep learning
title Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
title_full Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
title_fullStr Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
title_full_unstemmed Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
title_short Federated Subgraph Learning via Global-Knowledge-Guided Node Generation
title_sort federated subgraph learning via global knowledge guided node generation
topic federated learning
distributed learning
graph learning
machine learning
deep learning
url https://www.mdpi.com/1424-8220/25/7/2240
work_keys_str_mv AT yuxuanliu federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT zhiminghe federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT shuangwang federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT yangyangwang federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT peichaowang federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT zhangshenhuang federatedsubgraphlearningviaglobalknowledgeguidednodegeneration
AT qisun federatedsubgraphlearningviaglobalknowledgeguidednodegeneration