用语言语义增强图神经网络的节点交互建模能力
Refining Interactions: Enhancing Anisotropy in Graph Neural Networks with Language Semantics
- 将语言语义引入图结构，动态捕捉节点间独特关系
- 在多个数据集上优于现有方法，且无需增加计算复杂度
- 适合需要精细关系建模的文本图任务
将大语言模型（LLM）与图神经网络（GNN）结合以增强文本属性图（TAGs）的能力近年来受到关注。现有方法通常直接将图结构或邻接节点的文本描述输入LLM，但这些方法常使LLM将结构信息视为一般上下文文本，限制了其在图任务中的表现。本文提出LanSAGNN（语言语义异向图神经网络），将异向GNN的概念扩展至自然语言层面。该模型利用LLM为节点对提取定制化的语义信息，有效捕捉节点间独特交互。此外，我们设计了一种高效的双层LLM微调架构，更好地对齐LLM输出与图任务需求。实验表明，LanSAGNN在不增加复杂度的前提下显著提升现有基于LLM的方法性能，并展现出对干扰的强鲁棒性。
原文摘要 · Abstract (English)
The integration of Large Language Models (LLMs) with Graph Neural Networks (GNNs) has recently been explored to enhance the capabilities of Text Attribute Graphs (TAGs). Most existing methods feed textual descriptions of the graph structure or neighbouring nodes' text directly into LLMs. However, these approaches often cause LLMs to treat structural information simply as general contextual text, thus limiting their effectiveness in graph-related tasks. In this paper, we introduce LanSAGNN (Language Semantic Anisotropic Graph Neural Network), a framework that extends the concept of anisotropic GNNs to the natural language level. This model leverages LLMs to extract tailor-made semantic information for node pairs, effectively capturing the unique interactions within node relationships. In addition, we propose an efficient dual-layer LLMs finetuning architecture to better align LLMs' outputs with graph tasks. Experimental results demonstrate that LanSAGNN significantly enhances existing LLM-based methods without increasing complexity while also exhibiting strong robustness against interference.
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。