G-Censor: Graph Contrastive Learning with Task-Oriented Counterfactual Views

tianqianjin lin, Yangyang Kang, Zhuoren Jiang, Xurui Li, Changlong Sun, cui huang, Xiaozhong Liu

Keywords: graph contrastive learning, node property prediction, task-oriented counterfactual views

TL;DR: Graph Contrastive learning with task-oriented counterfactual positive/negative views, a model-agnostic framework designed for node property prediction tasks.

Abstract: Graph Contrastive learning (GCL) has achieved great success in learning representations from unlabeled graph-structure data. However, how to automatically obtain the optimal contrastive views w.r.t specific downstream tasks is little studied. Theoretically, a downstream task can be causally correlated to particular sub-structures in graphs. The existing GCL methods may fail to enhance model performance on a given task when the task-related semantics are incomplete/preserved in the positive/negative views. To address this problem, we propose G-CENSOR, i.e., Graph Contrastive lEarniNg with taSk-oriented cOunteRfactual views, a model-agnostic framework designed for node property prediction tasks. G-CENSOR can simultaneously generate the optimal task-oriented counterfactual positive/negative views for raw ego-graphs and train graph neural networks (GNNs) with a contrastive objective between the raw ego-graphs and their corresponding counterfac-tual views. Extensive experiments on eight real-world datasets demonstrate that G-CENSOR can consistently outperform existing state-of-the-art GCL methods to improve the task performance and generalizability of a series of typical GNNs. To the best of our knowledge, this is a pioneer investigation to explore task-oriented graph contrastive learning from a counterfactual perspective in node property pre- diction tasks. We will release the source code after the review process.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning