统一文本语义与图结构：面向时序文本属性图的大语言模型方法
Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
AI总结：
针对时序文本属性图中文本语义动态演化与结构信息交互不足的问题，提出CROSS框架，利用大语言模型提取时序语义并统一语义与结构，在多个数据集上显著提升链接预测与节点分类性能。
摘要：
时序图神经网络（TGNN）在时序图建模中已展现出卓越的性能。然而，现实世界中的时序图往往蕴含丰富的文本信息，由此产生了时序文本属性图（TTAG）。动态文本语义与演化图结构的结合带来了更高的复杂性。现有TGNN对文本进行静态嵌入，并严重依赖偏向于结构信息的编码机制，忽视了文本语义的时序演化以及语义与结构之间协同强化的关键交互。为解决这些问题，我们提出了CROSS，一个灵活框架，可无缝扩展现有TGNN以进行TTAG建模。CROSS的设计将TTAG建模过程分解为两个阶段：（i）时序语义提取；（ii）语义-结构信息统一。其关键思想是推进大语言模型（LLM）在文本空间中动态提取时序语义，进而生成统一语义与结构的连贯表示。具体而言，我们在CROSS框架中提出了时序语义提取器，使LLM能够对节点文本邻域的演化上下文提供时序语义理解，促进语义动态。随后，我们引入了语义-结构协同编码器，与上述提取器协作，通过同时考虑语义和结构信息并鼓励二者相互强化，合成具有启发性的表示。大量实验表明，CROSS在四个公共数据集和一个工业数据集上取得了最先进的结果，在时序链接预测中平均绝对MRR提升24.7%，在工业应用的节点分类中AUC提升3.7%。
英文摘要：
Temporal graph neural networks (TGNNs) have shown remarkable performance in temporal graph modeling. However, real-world temporal graphs often possess rich textual information, giving rise to temporal text-attributed graphs (TTAGs). Such combination of dynamic text semantics and evolving graph structures introduces heightened complexity. Existing TGNNs embed texts statically and rely heavily on encoding mechanisms that biasedly prioritize structural information, overlooking the temporal evolution of text semantics and the essential interplay between semantics and structures for synergistic reinforcement. To tackle these issues, we present \textbf{CROSS}, a flexible framework that seamlessly extends existing TGNNs for TTAG modeling. CROSS is designed by decomposing the TTAG modeling process into two phases: (i) temporal semantics extraction; and (ii) semantic-structural information unification. The key idea is to advance the large language models (LLMs) to dynamically extract the temporal semantics in text space and then generate cohesive representations unifying both semantics and structures. Specifically, we propose a Temporal Semantics Extractor in the CROSS framework, which empowers LLMs to offer the temporal semantic understanding of node's evolving contexts of textual neighborhoods, facilitating semantic dynamics. Subsequently, we introduce the Semantic-structural Co-encoder, which collaborates with the above Extractor for synthesizing illuminating representations by jointly considering both semantic and structural information while encouraging their mutual reinforcement. Extensive experiments show that CROSS achieves state-of-the-art results on four public datasets and one industrial dataset, with 24.7% absolute MRR gain on average in temporal link prediction and 3.7% AUC gain in node classification of industrial application.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
