Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)

TL;DR

This paper introduces ExGNAS, an explainable graph neural architecture search method that uses a simple, adaptable search space and Monte-Carlo tree search to find accurate GNN models efficiently, with added interpretability.

Contribution

The paper presents a novel explainable Graph NAS approach combining a simple search space with Monte-Carlo tree search for better accuracy, efficiency, and interpretability.

Findings

ExGNAS achieves up to 26.1% higher accuracy.

Reduces search run time by up to 88%.

Proves effectiveness of explainability through user study.

Abstract

The number of graph neural network (GNN) architectures has increased rapidly due to the growing adoption of graph analysis. Although we use GNNs in wide application scenarios, it is a laborious task to design/select optimal GNN architectures in diverse graphs. To reduce human efforts, graph neural architecture search (Graph NAS) has been used to search for a sub-optimal GNN architecture that combines existing components. However, existing Graph NAS methods lack explainability to understand the reasons why the model architecture is selected because they use complex search space and neural models to select architecture. Therefore, we propose an explainable Graph NAS method, called ExGNAS, which consists of (i) a simple search space that can adapt to various graphs and (ii) a search algorithm with Monte-Carlo tree that makes the decision process explainable. The combination of our search space and algorithm achieves finding accurate GNN models and the important functions within the search space. We comprehensively evaluate ExGNAS compared with four state-of-the-art Graph NAS methods in twelve graphs. Our experimental results show that ExGNAS achieves high average accuracy and efficiency; improving accuracy up to 26.1% and reducing run time up to 88%. Furthermore, we show the effectiveness of explainability by questionnaire-based user study and architecture analysis.