GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Haotong, Wang, Xiyuan, Tao, Qian, Hu, Shuxian, Lin, Zhouchen, Zhang, Muhan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915055351627776
author Yang, Haotong
Wang, Xiyuan
Tao, Qian
Hu, Shuxian
Lin, Zhouchen
Zhang, Muhan
author_facet Yang, Haotong
Wang, Xiyuan
Tao, Qian
Hu, Shuxian
Lin, Zhouchen
Zhang, Muhan
contents Recent research on integrating Large Language Models (LLMs) with Graph Neural Networks (GNNs) typically follows two approaches: LLM-centered models, which convert graph data into tokens for LLM processing, and GNN-centered models, which use LLMs to encode text features into node and edge representations for GNN input. LLM-centered models often struggle to capture graph structures effectively, while GNN-centered models compress variable-length textual data into fixed-size vectors, limiting their ability to understand complex semantics. Additionally, GNN-centered approaches require converting tasks into a uniform, manually-designed format, restricting them to classification tasks and preventing language output. To address these limitations, we introduce a new architecture that deeply integrates GNN with LLM, featuring three key innovations: (1) Structure-Aware Transformers, which incorporate GNN's message-passing capabilities directly into LLM's transformer layers, allowing simultaneous processing of textual and structural information and generating outputs from both GNN and LLM; (2) Graph-Text Cross-Attention, which processes full, uncompressed text from graph nodes and edges, ensuring complete semantic integration; and (3) GNN-LLM Twin Predictor, enabling LLM's flexible autoregressive generation alongside GNN's scalable one-pass prediction. GL-Fusion achieves outstand performance on various tasks. Notably, it achieves state-of-the-art performance on OGBN-Arxiv and OGBG-Code2.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
Yang, Haotong
Wang, Xiyuan
Tao, Qian
Hu, Shuxian
Lin, Zhouchen
Zhang, Muhan
Machine Learning
Artificial Intelligence
Computation and Language
Recent research on integrating Large Language Models (LLMs) with Graph Neural Networks (GNNs) typically follows two approaches: LLM-centered models, which convert graph data into tokens for LLM processing, and GNN-centered models, which use LLMs to encode text features into node and edge representations for GNN input. LLM-centered models often struggle to capture graph structures effectively, while GNN-centered models compress variable-length textual data into fixed-size vectors, limiting their ability to understand complex semantics. Additionally, GNN-centered approaches require converting tasks into a uniform, manually-designed format, restricting them to classification tasks and preventing language output. To address these limitations, we introduce a new architecture that deeply integrates GNN with LLM, featuring three key innovations: (1) Structure-Aware Transformers, which incorporate GNN's message-passing capabilities directly into LLM's transformer layers, allowing simultaneous processing of textual and structural information and generating outputs from both GNN and LLM; (2) Graph-Text Cross-Attention, which processes full, uncompressed text from graph nodes and edges, ensuring complete semantic integration; and (3) GNN-LLM Twin Predictor, enabling LLM's flexible autoregressive generation alongside GNN's scalable one-pass prediction. GL-Fusion achieves outstand performance on various tasks. Notably, it achieves state-of-the-art performance on OGBN-Arxiv and OGBG-Code2.
title GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2412.06849