Saved in:
Bibliographic Details
Main Authors: Zhang, Jiaxing, Liu, Jiayi, Luo, Dongsheng, Neville, Jennifer, Wei, Hua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.15351
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910538812882944
author Zhang, Jiaxing
Liu, Jiayi
Luo, Dongsheng
Neville, Jennifer
Wei, Hua
author_facet Zhang, Jiaxing
Liu, Jiayi
Luo, Dongsheng
Neville, Jennifer
Wei, Hua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15351
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
Zhang, Jiaxing
Liu, Jiayi
Luo, Dongsheng
Neville, Jennifer
Wei, Hua
Machine Learning
Artificial Intelligence
Computation and Language
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.
title LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2407.15351