将图结构与文本语义双向融合，提升文本属性图的表示学习效果。
Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex
- 通过双向注意力机制实现文本与图结构的深度交互
- 在五个基准数据集上达到当前最优节点分类性能
- 适配大模型且无需全量微调，适合资源有限场景
文本属性图（TAGs）在表示学习中面临独特挑战，需同时捕捉节点文本的语义丰富性与图的结构依赖关系。图神经网络（GNNs）擅长建模拓扑信息，但无法处理非结构化文本；大语言模型（LLMs）擅长文本理解，却通常忽视图结构。本文提出BiGTex（双向图文本），一种通过堆叠图-文本融合单元紧密集成GNN与LLM的新架构。每个单元支持文本与结构表征间的相互注意力，实现双向信息流动：文本影响结构，结构引导文本理解。该架构采用参数高效微调（LoRA）训练，冻结LLM并仅适应任务信号。在五个基准数据集上的实验表明，BiGTex在节点分类任务中达到顶尖性能，并有效泛化至链接预测。消融研究进一步验证了软提示与双向注意力对模型成功的关键作用。
原文摘要 · Abstract (English)
Text-attributed graphs (TAGs) present unique challenges in representation learning by requiring models to capture both the semantic richness of node-associated texts and the structural dependencies of the graph. While graph neural networks (GNNs) excel at modeling topological information, they lack the capacity to process unstructured text. Conversely, large language models (LLMs) are proficient in text understanding but are typically unaware of graph structure. In this work, we propose BiGTex (Bidirectional Graph Text), a novel architecture that tightly integrates GNNs and LLMs through stacked Graph-Text Fusion Units. Each unit allows for mutual attention between textual and structural representations, enabling information to flow in both directions, text influencing structure and structure guiding textual interpretation. The proposed architecture is trained using parameter-efficient fine-tuning (LoRA), keeping the LLM frozen while adapting to task-specific signals. Extensive experiments on five benchmark datasets demonstrate that BiGTex achieves state-of-the-art performance in node classification and generalizes effectively to link prediction. An ablation study further highlights the importance of soft prompting and bi-directional attention in the model's success.
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。