RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks

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

Keywords: Graph Neural Networks, Graph Explanation, Graph Regression

TL;DR: Our paper firstly explores the explainabality fn the GNNs in the regression task.

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 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 information bottleneck theory and a new mix-up framework,
which could support various GNNs in a model-agnostic manner.
Additionally, we present a contrastive 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

Submission Type: Extended abstract (max 4 main pages).

Submission Number: 149