RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks

Jiaxing Zhang, Zhuomin Chen, hao mei, Longchao Da, Dongsheng Luo, Hua Wei

Keywords: graph neural network, explainability, data augmentation

TL;DR: This work extend the graph information bottleneck from graph classification tasks to the graph regression tasks.

Abstract:

Graph regression is a fundamental task that has gained significant attention in
various graph learning tasks. However, the inference process is often not easily
interpretable. Current explanation techniques are limited to understanding Graph
Neural Network (GNN) behaviors in classification tasks, leaving an explanation gap
for graph regression models. In this work, we propose a novel explanation method
to interpret the graph regression models (XAIG-R). Our method addresses the
distribution shifting problem and continuously ordered decision boundary issues
that hinder existing methods away from being applied in regression tasks. We
introduce a novel objective based on the graph information bottleneck theory (GIB)
and a new mix-up framework, which can support various GNNs and explainers
in a model-agnostic manner. Additionally, we present a self-supervised learning
strategy to tackle the continuously ordered labels in regression tasks. We evaluate
our proposed method on three benchmark datasets and a real-life dataset introduced
by us, and extensive experiments demonstrate its effectiveness in interpreting GNN
models in regression tasks.

Primary Area: Interpretability and explainability

Submission Number: 8021