Large Language Model Enhancers for Graph Neural Networks: An Analysis from the Perspective of Causal Mechanism Identification
The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provide data for analysis. Using this dataset, we conduct interchange interventions to examine the deeper properties of LLM enhancers and GNNs, uncovering their underlying logic and internal mechanisms. Building on the analytical results, we design a plug-and-play optimization module to improve the information transfer between LLM enhancers and GNNs. Experiments across multiple datasets and models validate the proposed module.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Representation LearningLanguage ModelingLanguage ModellingLarge Language ModelRepresentation LearningSimilar Papers 제목 키워드 기반
Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing tasks. Recently, several LLMs-based pipelines have been developed to enhance learning on graphs with text a…
Role of distal enhancers in shaping 3D-folding patterns and defining human-specific features of interphase chromatin architecture in embryonic stem cells
Molecular and genetic definitions of human-specific changes to genomic regulatory networks (GRNs) contributing to development of unique to human phenotypes remain a highly significant challenge. Genome-wide proximity pla…
Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features, giving rise to LLM-enhanced GNNs that achieve notable performance gains. However, the robu…
APE: Agentic Prompt Enhancer for Image Generation and Editing
Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt formulation. Semantically similar requests can produce different outputs…
Image GenerationLeveraging Multiple Speech Enhancers for Non-Intrusive Intelligibility Prediction for Hearing-Impaired Listeners
Speech intelligibility evaluation for hearing-impaired (HI) listeners is essential for assessing hearing aid performance, traditionally relying on listening tests or intrusive methods like HASPI. However, these methods r…