GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks

2024/02/11 by Mengmei Zhang, Mingwei Sun, Zhang, Mengmei +15 · 8 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2402.07197

openalex publication_date 2024/02/11 · openalex created_date 2024/02/15 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, with LLM as a node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-text alignment data along node information, neighbor information and model information. By translating node representation into tokens, GraphTranslator empowers an LLM to make predictions based on language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results demonstrate the effectiveness of our proposed GraphTranslator on zero-shot node classification. The graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended tasks through language instructions. Our code is available at: https://github.com/alibaba/GraphTranslator.

Cited by

• Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning
• Graph4MM: Weaving Multimodal Learning with Structural Information
• UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
• InterCorpRel-LLM: Enhancing Financial Relational Understanding with Graph-Language Models
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
• CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials
• Matching Game Preferences Through Dialogical Large Language Models: A Perspective
• Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily

Related

• UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
• GraphGPT: Graph Instruction Tuning for Large Language Models
• Enhance Graph Alignment for Large Language Models
• GraphText: Graph Reasoning in Text Space
• GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability