LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
This addresses learning bias issues in GNN interpretability, which is an incremental improvement for researchers and practitioners in graph machine learning.
The paper tackles the problem of learning bias in Graph Neural Network (GNN) explanation methods due to dataset scarcity by embedding a Large Language Model (LLM) as a Bayesian Inference module to mitigate bias, with efficacy proven theoretically and experimentally on synthetic and real-world datasets.
Recent studies seek to provide Graph Neural Network (GNN) interpretability via multiple unsupervised learning models. Due to the scarcity of datasets, current methods easily suffer from learning bias. To solve this problem, we embed a Large Language Model (LLM) as knowledge into the GNN explanation network to avoid the learning bias problem. We inject LLM as a Bayesian Inference (BI) module to mitigate learning bias. The efficacy of the BI module has been proven both theoretically and experimentally. We conduct experiments on both synthetic and real-world datasets. The innovation of our work lies in two parts: 1. We provide a novel view of the possibility of an LLM functioning as a Bayesian inference to improve the performance of existing algorithms; 2. We are the first to discuss the learning bias issues in the GNN explanation problem.