GraphGPT：面向大语言模型的图指令微调
GraphGPT: Graph Instruction Tuning for Large Language Models
AI总结：
GraphGPT通过图指令微调将大语言模型与图结构知识融合，提出文本-图 grounding 和双阶段对齐投影器，在无需下游图数据的情况下实现有监督与零样本图学习的优越泛化。
摘要：
图神经网络（GNNs）通过节点间的递归交换与聚合来理解图结构。为增强鲁棒性，自监督学习（SSL）已成为数据增强的重要工具。传统方法通常依赖任务特定标签的微调，这在标注数据稀缺时限制了其有效性。我们的研究通过在零样本学习环境中推进图模型泛化来应对这一问题。受大语言模型（LLMs）成功的启发，我们旨在构建一个面向图的LLM，能够在不依赖下游图数据的情况下，在各类数据集和任务上具备出色的泛化能力。我们提出GraphGPT框架，通过图指令微调将LLMs与图结构知识相结合。该框架包含一个文本-图 grounding 组件，用于连接文本结构与图结构，以及一种双阶段指令微调方法，并配备轻量级图-文本对齐投影器。这些创新使LLMs能够理解复杂图结构，并增强其在多样数据集和任务上的适应性。我们的框架在有监督和零样本图学习任务中均展现出优越的泛化能力，超越了现有基准。我们GraphGPT的开源模型实现可在 https://github.com/HKUDS/GraphGPT 获取。
英文摘要：
Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization across various datasets and tasks without relying on downstream graph data. We introduce the GraphGPT framework, which integrates LLMs with graph structural knowledge through graph instruction tuning. This framework includes a text-graph grounding component to link textual and graph structures and a dual-stage instruction tuning approach with a lightweight graph-text alignment projector. These innovations allow LLMs to comprehend complex graph structures and enhance adaptability across diverse datasets and tasks. Our framework demonstrates superior generalization in both supervised and zero-shot graph learning tasks, surpassing existing benchmarks. The open-sourced model implementation of our GraphGPT is available at https://github.com/HKUDS/GraphGPT.
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。
