Saved in:
Bibliographic Details
Main Authors: Hu, Zhengyu, Li, Yichuan, Chen, Zhengyu, Wang, Jingang, Liu, Han, Lee, Kyumin, Ding, Kaize
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.07074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912366769209344
author Hu, Zhengyu
Li, Yichuan
Chen, Zhengyu
Wang, Jingang
Liu, Han
Lee, Kyumin
Ding, Kaize
author_facet Hu, Zhengyu
Li, Yichuan
Chen, Zhengyu
Wang, Jingang
Liu, Han
Lee, Kyumin
Ding, Kaize
contents Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured data. We introduce AskGNN, a novel approach that bridges this gap by leveraging In-Context Learning (ICL) to integrate graph data and task-specific information into LLMs. AskGNN employs a Graph Neural Network (GNN)-powered structure-enhanced retriever to select labeled nodes across graphs, incorporating complex graph structures and their supervision signals. Our learning-to-retrieve algorithm optimizes the retriever to select example nodes that maximize LLM performance on graph. Experiments across three tasks and seven LLMs demonstrate AskGNN's superior effectiveness in graph task performance, opening new avenues for applying LLMs to graph-structured data without extensive fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07074
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning
Hu, Zhengyu
Li, Yichuan
Chen, Zhengyu
Wang, Jingang
Liu, Han
Lee, Kyumin
Ding, Kaize
Machine Learning
Textual Attributed Graphs (TAGs) are crucial for modeling complex real-world systems, yet leveraging large language models (LLMs) for TAGs presents unique challenges due to the gap between sequential text processing and graph-structured data. We introduce AskGNN, a novel approach that bridges this gap by leveraging In-Context Learning (ICL) to integrate graph data and task-specific information into LLMs. AskGNN employs a Graph Neural Network (GNN)-powered structure-enhanced retriever to select labeled nodes across graphs, incorporating complex graph structures and their supervision signals. Our learning-to-retrieve algorithm optimizes the retriever to select example nodes that maximize LLM performance on graph. Experiments across three tasks and seven LLMs demonstrate AskGNN's superior effectiveness in graph task performance, opening new avenues for applying LLMs to graph-structured data without extensive fine-tuning.
title Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning
topic Machine Learning
url https://arxiv.org/abs/2410.07074