Author:
Zeng Zhuo,Xie Jianyu,Yang Zhijie,Ma Tengfei,Chen Duanbing
Abstract
AbstractGraph domain adaptation (GDA) aims to address the challenge of limited label data in the target graph domain. Existing methods such as UDAGCN, GRADE, DEAL, and COCO for different-level (node-level, graph-level) adaptation tasks exhibit variations in domain feature extraction, and most of them solely rely on representation alignment to transfer label information from a labeled source domain to an unlabeled target domain. However, this approach can be influenced by irrelevant information and usually ignores the conditional shift of the downstream predictor. To effectively address this issue, we introduce a target-oriented unsupervised graph domain adaptive framework for graph adaptation called TO-UGDA. Particularly, domain-invariant feature representations are extracted using graph information bottleneck. The discrepancy between two domains is minimized using an adversarial alignment strategy to obtain a unified feature distribution. Additionally, the meta pseudo-label is introduced to enhance downstream adaptation and improve the model’s generalizability. Through extensive experimentation on real-world graph datasets, it is proved that the proposed framework achieves excellent performance across various node-level and graph-level adaptation tasks.
Funder
National Natural Science Foundation of China
Publisher
Springer Science and Business Media LLC
Reference66 articles.
1. Liu, Z., Nguyen, T.-K. & Fang, Y. Tail-gnn: Tail-node graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 1109–1119 (2021).
2. Dai, E., Jin, W., Liu, H. & Wang, S. Towards robust graph neural networks for noisy graphs with sparse labels. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, 181–191 (2022).
3. Suresh, S., Li, P., Hao, C. & Neville, J. Adversarial graph augmentation to improve graph contrastive learning. In Proceedings of the International Conference on Neural Information Processing Systems (2021).
4. Xu, D., Cheng, W., Luo, D., Chen, H. & Zhang, X. Infogcl: Information-aware graph contrastive learning. In Proceedings of the International Conference on Neural Information Processing Systems (2021).
5. Jiang, B., Kloster, K., Gleich, D. F. & Gribskov, M. Aptrank: an adaptive pagerank model for protein function prediction on bi-relational graphs. Bioinformatics 33, 1829–1836 (2017).