Graph Neural Networks (GNNs) have empowered the advance in graph-structured data analysis. Recently, the rise of Large Language Models (LLMs) like GPT-4 has heralded a new era in deep learning. However, their application to graph data poses distinct challenges due to the inherent difficulty of translating graph structures to language. To this end, we introduce the Large Language and Graph Assistant (LLaGA), an innovative model that effectively integrates LLM capabilities to handle the complexities of graph-structured data. LLaGA retains the general-purpose nature of LLMs while adapting graph data into a format compatible with LLM input. LLaGA achieves this by reorganizing graph nodes to structure-aware sequences and then mapping these into the token embedding space through a versatile projector. LLaGA excels in versatility, generalizability and interpretability, allowing it to perform consistently well across different datasets and tasks, extend its ability to unseen datasets or tasks, and provide explanations for graphs. Our extensive experiments across popular graph benchmarks show that LLaGA delivers outstanding performance across four datasets and three tasks using one single model, surpassing state-of-the-art graph models in both supervised and zero-shot scenarios. Our code is available at \url{https://github.com/VITA-Group/LLaGA}.

翻译：图神经网络（GNN）推动了图结构数据分析领域的发展。近期，GPT-4等大型语言模型（LLM）的兴起标志着深度学习新纪元的到来。然而，由于将图结构转化为语言表达存在固有困难，将其应用于图数据面临独特挑战。为此，我们提出大型语言与图辅助模型（LLaGA），这是一种创新模型，能够有效整合LLM能力以处理图结构数据的复杂性。LLaGA在保持LLM通用性的同时，将图数据适配为兼容LLM输入的格式。该模型通过将图节点重组为结构感知序列，并利用通用投影器将这些序列映射至词元嵌入空间来实现这一目标。LLaGA在通用性、泛化能力和可解释性方面表现卓越，能够在不同数据集和任务中保持稳定性能，将能力扩展至未见过的数据集或任务，并为图提供解释。我们在主流图基准上的大量实验表明，LLaGA使用单一模型即可在四个数据集和三个任务上取得卓越表现，在监督学习和零样本场景中均超越现有最优图模型。我们的代码已开源至 \url{https://github.com/VITA-Group/LLaGA}。