UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
This work addresses the underexplored problem of explaining unsupervised node embeddings, providing a method for understanding downstream tasks like link prediction and clustering.
The paper introduces UNR-Explainer, a method for generating counterfactual explanations for unsupervised node representation learning models. It uses Monte Carlo Tree Search to identify subgraphs that significantly alter a node's k-nearest neighbors in the embedding space, achieving superior performance on datasets for GraphSAGE and DGI.
Node representation learning, such as Graph Neural Networks (GNNs), has emerged as a pivotal method in machine learning. The demand for reliable explanation generation surges, yet unsupervised models remain underexplored. To bridge this gap, we introduce a method for generating counterfactual (CF) explanations in unsupervised node representation learning. We identify the most important subgraphs that cause a significant change in the k-nearest neighbors of a node of interest in the learned embedding space upon perturbation. The k-nearest neighbor-based CF explanation method provides simple, yet pivotal, information for understanding unsupervised downstream tasks, such as top-k link prediction and clustering. Consequently, we introduce UNR-Explainer for generating expressive CF explanations for Unsupervised Node Representation learning methods based on a Monte Carlo Tree Search (MCTS). The proposed method demonstrates superior performance on diverse datasets for unsupervised GraphSAGE and DGI.