CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks

2021/02/05 by Lucic, Ana, ter Hoeve, Maartje, Tolomei, Gabriele +2 · 8 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2102.03322

Abstract

Given the increasing promise of graph neural networks (GNNs) in real-world applications, several methods have been developed for explaining their predictions. Existing methods for interpreting predictions from GNNs have primarily focused on generating subgraphs that are especially relevant for a particular prediction. However, such methods are not counterfactual (CF) in nature: given a prediction, we want to understand how the prediction can be changed in order to achieve an alternative outcome. In this work, we propose a method for generating CF explanations for GNNs: the minimal perturbation to the input (graph) data such that the prediction changes. Using only edge deletions, we find that our method, CF-GNNExplainer, can generate CF explanations for the majority of instances across three widely used datasets for GNN explanations, while removing less than 3 edges on average, with at least 94% accuracy. This indicates that CF-GNNExplainer primarily removes edges that are crucial for the original predictions, resulting in minimal CF explanations.

Cited by

• TrendGNN: Towards Understanding of Epidemics, Beliefs, and Behaviors
• ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
• Interpreting GFlowNets for Drug Discovery: Extracting Actionable Insights for Medicinal Chemistry
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models
• Mitigating Popularity Bias in Counterfactual Explanations using Large Language Models
• Learning to Locate: GNN-Powered Vulnerability Path Discovery in Open Source Code
• Geometric deep learning assists protein engineering. Opportunities and Challenges

Related

• Robust Counterfactual Explanations on Graph Neural Networks
• Global Counterfactual Explainer for Graph Neural Networks
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Global Graph Counterfactual Explanation: A Subgraph Mapping Approach
• Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivity