TemporalGraphLLM：面向动态文本属性图的时间图神经网络与大语言模型
TemporalGraphLLM: Temporal Graph Neural Networks with Large Language Models for Dynamic Text-Attributed Graphs
中文总结 AI 辅助
提出TemporalGraphLLM框架，集成时间图神经网络与大语言模型，通过图时间感知指令微调和图嵌入注入，在动态文本属性图的边分类、链接预测和文本生成任务上达到最先进性能。
中文摘要 AI 辅助
动态文本属性图（DTAGs）中，节点、边和文本属性随时间演化，在社交网络、引文图和知识图谱等应用中至关重要。然而，现有方法难以同时建模图结构的时间演化与文本属性的语义丰富性。时间图神经网络（TGNNs）虽能捕捉不断演化的节点关系，但往往缺乏上下文文本推理能力。相反，大语言模型（LLMs）擅长文本理解，但在时间设置下的结构化图推理方面存在困难。为弥合这一差距，我们提出TemporalGraphLLM，一种新颖框架，可将任意时间GNN与LLM集成，以增强DTAGs中的推理能力。我们的方法通过图时间感知指令微调和新型时间GNN注入来微调LLMs，用图嵌入替代专用添加令牌。TemporalGraphLLM有效利用预训练TGNNs于LLM框架内，在边分类、链接预测和基于边的文本生成任务上实现最先进性能。对真实世界动态图数据集的广泛评估证明了其最先进性能。我们的发现凸显了LLMs与TGNNs的协同潜力，为演化图学习开辟了新方向。
英文摘要
Dynamic text-attributed graphs (DTAGs), where nodes, edges, and textual attributes evolve over time, are crucial in applications such as social networks, citation graphs, and knowledge graphs. However, existing approaches struggle to jointly model the temporal evolution of graph structures and the semantic richness of textual attributes. While Temporal Graph Neural Networks (TGNNs) capture evolving node relationships, they often lack contextual text reasoning. Conversely, Large Language Models (LLMs) excel in textual understanding but struggle with structured graph reasoning in temporal settings. To bridge this gap, we propose TemporalGraphLLM, a novel framework that can integrate any temporal GNN with an LLM for enhanced reasoning in DTAGs. Our approach fine-tunes LLMs using graph-time-aware instruction tuning and novel temporal GNNs injection to replace dedicated added tokens with graph embeddings. TemporalGraphLLM effectively leverages pretrained TGNNs within an LLM framework to achieve state-of-the-art performance on edge classification, link prediction, and edge-based text generation tasks. Extensive evaluation on real-world dynamic graph datasets demonstrates state-of-the-art performance. Our findings highlight the synergistic potential of LLMs and TGNNs, opening new directions for learning on evolving graphs.
