Adversarial Mask Explainer for Graph Neural Networks
Keywords: Explainability, Graph Neural Networks, Graph Analysis
TL;DR: The objective of this study is to explain a trained graph neural networks model by providing a sparse selection of informative edges.
Abstract: The Graph Neural Networks (GNNs) model is a powerful tool for integrating node information with graph topology to learn representations and make predictions. However, the complex graph structure of GNNs has led to a lack of clear explainability in the decision-making process. Recently, there has been a growing interest in seeking instance-level explanations of the GNNs model, which aims to uncover the decision-making process of the GNNs model and provide insights into how it arrives at its final output. Previous works have focused on finding a set of weights (masks) for edges/nodes/node features to determine their importance. These works have adopted a regularization term and a hyperparameter $K$ to control the explanation size during the training process and keep only the top-$K$ weights as the explanation set. However, the true size of the explanation is typically unknown to users, making it difficult to provide reasonable values for the regularization term and $K$. In this work, we propose a novel framework AMExplainer which leverages the concept of adversarial networks to achieve a dual optimization objective in the target function. This approach ensures both accurate prediction of the mask and sparsity of the explanation set. In addition, we devise a novel scaling function to automatically sense and amplify the weights of the informative part of the graph, which filters out insignificant edges/nodes/node features for expediting the convergence of the solution during training. Our extensive experiments show that AMExplainer yields a more compelling explanation by generating a sparse set of masks while simultaneously maintaining fidelity.
Track: Graph Algorithms and Learning for the Web
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 1775
Loading