Counterfactual Learning on Graphs: A Survey
Zhimeng Guo, Teng Xiao, Zongyu Wu, Charu Aggarwal, Hui Liu, Suhang Wang
TL;DR
This survey introduces graph counterfactual learning as a unifying framework to address biases, interpretability, and causal reasoning on graph-structured data. It systematically categorizes approaches into four areas—counterfactual fairness, counterfactual explanations, counterfactual link prediction, and applications—and provides unified frameworks, taxonomy, datasets, and evaluation metrics. By detailing representative methods (e.g., NIFTY, GEAR, CFLP, KGCF, CR, UKGC, CGKR) and real-world applications across physical systems, medicine, and molecular domains, the work highlights how counterfactual thinking can mitigate bias, reveal causal factors, and improve robustness in graph learning. The paper also offers a curated repository of open-source implementations, datasets, and metrics, and outlines practical future directions including scalability, dynamic graphs, and unsupervised settings to advance graph counterfactual learning in real-world deployments.
Abstract
Graph-structured data are pervasive in the real-world such as social networks, molecular graphs and transaction networks. Graph neural networks (GNNs) have achieved great success in representation learning on graphs, facilitating various downstream tasks. However, GNNs have several drawbacks such as lacking interpretability, can easily inherit the bias of data and cannot model casual relations. Recently, counterfactual learning on graphs has shown promising results in alleviating these drawbacks. Various approaches have been proposed for counterfactual fairness, explainability, link prediction and other applications on graphs. To facilitate the development of this promising direction, in this survey, we categorize and comprehensively review papers on graph counterfactual learning. We divide existing methods into four categories based on problems studied. For each category, we provide background and motivating examples, a general framework summarizing existing works and a detailed review of these works. We point out promising future research directions at the intersection of graph-structured data, counterfactual learning, and real-world applications. To offer a comprehensive view of resources for future studies, we compile a collection of open-source implementations, public datasets, and commonly-used evaluation metrics. This survey aims to serve as a ``one-stop-shop'' for building a unified understanding of graph counterfactual learning categories and current resources. We also maintain a repository for papers and resources and will keep updating the repository https://github.com/TimeLovercc/Awesome-Graph-Causal-Learning.