Digging into the Landscape of Graphs Counterfactual Explainability

Abstract

In this lab, we provide a hands-on experience to help users develop and evaluate novel Graph Counterfactual Explanation (GCE) methods using a simple and modular framework, GRETEL. We will cover the main challenges of producing counterfactual explanations in the graph domain. We will show the participants how to build basic explanation pipelines in GRETEL. Furthermore, we show how the different categories of explainers can be implemented following the framework’s general logic and present an empirical study of their performance in different datasets. Moreover, we will instruct the participants on extending the frameworks’ main components to support custom GCE scenarios (i.e., new datasets, oracles, explainers, and evaluation measures).