FGTL: Federated Graph Transfer Learning for Node Classification
Open Access
- 29 November 2024
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (1) , 1-20
Abstract
Unsupervised multi-source domain transfer in federated scenario has become an emerging research direction, which can help unlabeled target domain to obtain the adapted model through source domains under privacy-preserving. However, when local data are graph, the difference of domains (or data heterogeneity) mainly originates from the difference in node attributes and sub-graph structures, leading to serious model drift, which is not considered by the existing related algorithms. Currently, there are two challenges in this scenario: (1) The node representations extracted directly through conventional GNNs lack inter-domain generalized and consistent information, making it difficult to apply existing federated learning algorithms. (2) The knowledge of source domains has quality differences, which may lead to negative transfer. To address these issues, we propose a novel two-phase Federated Graph Transfer Learning (FGTL) framework. In the generalization phase, FGTL utilizes local contrastive learning and global context embedding to force node representations to capture the inter-domain generalized and consistent information, lightly alleviating model drift. In the transfer phase, FGTL utilizes consensus knowledge to force the decision bound of classifier to adapt to the target client. In addition, FGTL+ exploits model grouping to make consensus knowledge generation more efficient, further enhancing the scalability of FGTL. Extensive experiments show that FGTL significantly outperforms state-of-the-art related methods, while FGTL+ further enhances privacy protection and reduces both communication and computation overhead.Keywords
Funding Information
- National Key R&D Program of China (2023YFB2703700)
- National Natural Science Foundation of China (62176269)
- Guangzhou Science and Technology Program (2023A04J0314)
This publication has 12 references indexed in Scilit:
- Federated adversarial domain generalization network: A novel machinery fault diagnosis method with data privacyKnowledge-Based Systems, 2022
- Federated knowledge graph completion via embedding-contrastive learningKnowledge-Based Systems, 2022
- Semi-Supervised Federated Heterogeneous Transfer LearningKnowledge-Based Systems, 2022
- Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning2022
- Graph Transfer Learning via Adversarial Domain Adaptation with Graph ConvolutionIEEE Transactions on Knowledge and Data Engineering, 2022
- Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling2021
- Model-Contrastive Federated Learning2021
- Network Together: Node Classification via Cross-Network Deep Network EmbeddingIEEE Transactions on Neural Networks and Learning Systems, 2020
- Unsupervised Domain Adaptive Graph Convolutional Networks2020
- ArnetMiner2008