SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks

TL;DR

This paper introduces SES, a self-explained and self-supervised GNN that jointly improves prediction accuracy and interpretability by generating explanations during training and enhancing representations through contrastive learning.

Contribution

SES uniquely combines explainable training with contrastive learning to improve both interpretability and prediction performance of GNNs.

Findings

SES produces high-quality explanations of node features and subgraphs.

SES improves prediction accuracy through contrastive learning.

SES reduces explanation generation time compared to existing methods.

Abstract

Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from GNNs' predictions, resulting in misrepresentations. Self-explainable GNNs offer built-in explanations during the training process. However, they cannot exploit the explanatory outcomes to augment prediction performance, and they fail to provide high-quality explanations of node features and require additional processes to generate explainable subgraphs, which is costly. To address the aforementioned limitations, we propose a self-explained and self-supervised graph neural network (SES) to bridge the gap between explainability and prediction. SES comprises two processes: explainable training and enhanced predictive learning. During explainable training, SES employs a global mask generator co-trained with a graph encoder and directly produces crucial structure and feature masks, reducing time consumption and providing node feature and subgraph explanations. In the enhanced predictive learning phase, mask-based positive-negative pairs are constructed utilizing the explanations to compute a triplet loss and enhance the node representations by contrastive learning.