Counterfactual Learning on Graphs:A Survey  

作　　者：Zhimeng Guo Zongyu Wu Teng Xiao Charu Aggarwal Hui Liu Suhang Wang 

机构地区：[1]College of Information Sciences and Technology,Pennsylvania State University,University Park 16802,USA [2]International Business Machines Corporation T.J.Watson Research Center,New York 10598,USA [3]College of Engineering,Michigan State University,East Lansing 48824,USA

出　　处：《Machine Intelligence Research》2025年第1期17-59,共43页机器智能研究(英文版)

基　　金：supported by,or in part by the National Science Foundation(NSF),USA(No.IIS-1909702);Army Research Office(ARO),USA(No.W911NF-21-10198),and Cisco Faculty Research Award.

摘　　要：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 rela-tions.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 develop-ment 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 ex-amples,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 evalu-ation metrics.This survey aims to serve as a“one-stop-shop”for building a unified understanding of graph counterfactual learning cat-egories and current resources.

关 键 词：Counterfactual learning graph-structured data graph neural networks FAIRNESS explainability 

分 类 号：O15[理学—数学]