DOI: 10.1145/3608953 ISSN:

Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation

Ying Chen, Siwei Qiang, Mingming Ha, Xiaolei Liu, Shaoshuai Li, Jiabi Tong, Lingfeng Yuan, Xiaobo Guo, Zhenfeng Zhu
  • General Computer Science

In recent years, semi-supervised graph learning with data augmentation (DA) has been the most commonly used and best-performing method to improve model robustness in the sparse scenarios with few labeled samples. However, most of existing DA methods are based on the homogeneous graph while none are specific for the heterogeneous graph. Differing from the homogeneous graph, DA in heterogeneous graph faces greater challenges: heterogeneity of information requires DA strategies to effectively handle heterogeneous relations, which considers the information contribution of different types of neighbors and edges to the target nodes. Furthermore, over-squashing of information is caused by the negative curvature that formed by the non-uniformity distribution and the strong clustering in complex graph. To address these challenges, this paper presents a novel method named Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation (HG-MDA). For the problem of heterogeneity of information in DA, node and topology augmentation strategies are proposed for the characteristics of heterogeneous graph. And meta-relation-based attention is applied as one of the indexes for selecting augmented nodes and edges. For the problem of over-squashing of information, triangle based edge adding and removing are designed to alleviate the negative curvature and bring the gain of topology. Finally, the loss function consists of the cross-entropy loss for labeled data and the consistency regularization for unlabeled data. In order to effectively fuse the prediction results of various DA strategies, the sharpening is used. Existing experiments on public datasets, i.e., ACM, DBLP, OGB, and industry dataset MB show that HG-MDA outperforms current SOTA models. Additionly, HG-MDA is applied to user identification in internet finance scenarios, helping the business to add 30% key users, and increase loans and balances by 3.6%, 11.1%, and 9.8%.

More from our Archive