LLaGA: Large Language and Graph Assistant

TL;DR

LLaGA is a novel model that integrates large language models with graph data processing, enabling versatile, interpretable, and high-performing analysis of graph-structured data across multiple tasks and datasets.

Contribution

It introduces a new approach to adapt LLMs for graph data by reorganizing nodes into sequences and mapping them into token space, achieving superior performance and interpretability.

Findings

Outperforms state-of-the-art graph models on multiple benchmarks

Effective in supervised and zero-shot learning scenarios

Provides explanations for graph data

Abstract

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}.