A first-of-its-kind national study co-authored by Associate Professor George Homsy at Binghamton University, State University of New York reveals a stark reality: minority communities, namely Black Americans, are paying a disproportionately higher share of their income to power their homes.

A new study led by the Konrad Lorenz Research Center for Behavior and Cognition at the University of Vienna sheds light on a long-standing mystery in animal behavior: why do certain individuals gain more influence than others within a group? The research shows that bold geese – but not aggressive ones – are more likely to be accepted as leaders, while exploratory individuals tend to follow them – revealing a nuanced interplay of personality and social roles in collective movement decisions. The results of the study have just been published in the journal iScience.

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, researchers categorize and comprehensively review papers on graph counterfactual learning. Researchers divide existing methods into four categories based on problems studied. For each category, they provide background and motivating examples, a general framework summarizing existing works and a detailed review of these works. Researchers 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, researchers 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.