用因果干预分析LLM增强图神经网络的机制，提升信息传递效果。
LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
- 通过可控合成数据集，用因果干预揭示LLM与GNN协同机制。
- 发现并优化了LLM与GNN间的信息传递瓶颈，提升节点表示质量。
- 模块可即插即用，适用于多种图模型与数据集，适配性强。
将大语言模型（LLM）作为特征增强器以优化节点表示，并将其输入图神经网络（GNN），在图表示学习中展现出显著潜力。然而，该方法的基本特性尚未得到充分探索。为此，本文基于互换干预方法开展更深入分析。首先，构建具有可控因果关系的合成图数据集，实现语义关系的精准操控与因果建模，为分析提供数据支持。利用该数据集，实施互换干预，深入探究LLM增强器与GNN的深层属性，揭示其内在逻辑与工作机制。基于分析结果，设计一个即插即用的优化模块，以提升LLM增强器与GNN之间的信息传递效率。在多个数据集和模型上的实验验证了所提模块的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。