Towards Self-Explainable Graph Neural Network

Abstract

Graph Neural Networks (GNNs), which generalize the deep neural networks to graph-structured data, have achieved great success in modeling graphs. However, as an extension of deep learning for graphs, GNNs lack explainability, which largely limits their adoption in scenarios that demand the transparency of models. Though many efforts are taken to improve the explainability of deep learning, they mainly focus on i.i.d data, which cannot be directly applied to explain the predictions of GNNs because GNNs utilize both node features and graph topology to make predictions. There are only very few work on the explainability of GNNs and they focus on post-hoc explanations. Since post-hoc explanations are not directly obtained from the GNNs, they can be biased and misrepresent the true explanations. Therefore, in this paper, we study a novel problem of self-explainable GNNs which can simultaneously give predictions and explanations. We propose a new framework which can find $K$-nearest labeled nodes for each unlabeled node to give explainable node classification, where nearest labeled nodes are found by interpretable similarity module in terms of both node similarity and local structure similarity. Extensive experiments on real-world and synthetic datasets demonstrate the effectiveness of the proposed framework for explainable node classification.

References in corpus (20)

• Distributed Representations of Words and Phrases and their Compositionality
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Learning Important Features Through Propagating Activation Differences
• Understanding Black-box Predictions via Influence Functions
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• struc2vec: Learning Node Representations from Structural Identity
• Adversarial Attacks on Neural Networks for Graph Data
• Simple and Deep Graph Convolutional Networks
• How Powerful are Graph Neural Networks?
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
• Parameterized Explainer for Graph Neural Network
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Molecular graph generation with Graph Neural Networks
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Self-supervised Training of Graph Convolutional Networks
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs