用大模型融合多个图神经网络，提升文本图数据的建模能力
Can Large Language Models Act as Ensembler for Multi-GNNs?
- 通过空间对齐让多图神经网络表示统一
- 用LoRA微调将图与文本信息注入大模型，实现联合建模
- 适合需要结合图结构与文本语义的场景
图神经网络（GNN）在处理图结构数据方面表现强劲，但缺乏对丰富文本节点属性的语义理解能力，限制了其应用效果。我们观察到，现有GNN模型在不同数据集上并无一个始终领先。本文研究大语言模型（LLM）能否作为多GNN的集成器，提出LensGNN模型：首先对齐多个GNN的表示空间；再通过LoRA微调，将图标记和文本信息注入LLM，建立GNN与LLM之间的对齐空间。该方法实现了多GNN的集成，并利用大模型优势，深化对文本语义与图结构信息的理解。实验表明，LensGNN优于现有模型。本研究为融合语义与结构信息的文本图集成学习提供了稳健且优越的解决方案。代码与数据已开源：https://github.com/AquariusAQ/LensGNN。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich textual node attributes, limiting their effectiveness in applications. On the other hand, we empirically observe that for existing GNN models, no one can consistently outperforms others across diverse datasets. In this paper, we study whether LLMs can act as an ensembler for multi-GNNs and propose the LensGNN model. The model first aligns multiple GNNs, mapping the representations of different GNNs into the same space. Then, through LoRA fine-tuning, it aligns the space between the GNN and the LLM, injecting graph tokens and textual information into LLMs. This allows LensGNN to ensemble multiple GNNs and take advantage of the strengths of LLM, leading to a deeper understanding of both textual semantic information and graph structural information. The experimental results show that LensGNN outperforms existing models. This research advances text-attributed graph ensemble learning by providing a robust and superior solution for integrating semantic and structural information. We provide our code and data here: https://github.com/AquariusAQ/LensGNN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。