Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining
Graph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of graph neural networks (GNNs). However, GNNs are still deficient...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/7/1147 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850212689818681344 |
|---|---|
| author | Yuxin You Zhen Liu Xiangchao Wen Yongtao Zhang Wei Ai |
| author_facet | Yuxin You Zhen Liu Xiangchao Wen Yongtao Zhang Wei Ai |
| author_sort | Yuxin You |
| collection | DOAJ |
| description | Graph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of graph neural networks (GNNs). However, GNNs are still deficient in generalizing to diverse graph data. Aiming to this issue, large language models (LLMs) could provide new solutions for graph mining tasks with their superior semantic understanding. In this review, we systematically review the combination and application techniques of LLMs and GNNs and present a novel taxonomy for research in this interdisciplinary field, which involves three main categories: GNN-driving-LLM(GdL), LLM-driving-GNN(LdG), and GNN-LLM-co-driving(GLcd). Within this framework, we reveal the capabilities of LLMs in enhancing graph feature extraction as well as improving the effectiveness of downstream tasks such as node classification, link prediction, and community detection. Although LLMs have demonstrated their great potential in handling graph-structured data, their high computational requirements and complexity remain challenges. Future research needs to continue to explore how to efficiently fuse LLMs and GNNs to achieve more powerful graph learning and reasoning capabilities and provide new impetus for the development of graph mining techniques. |
| format | Article |
| id | doaj-art-52e7b5c16c654cbd8cfa7912ea640b31 |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-52e7b5c16c654cbd8cfa7912ea640b312025-08-20T02:09:17ZengMDPI AGMathematics2227-73902025-03-01137114710.3390/math13071147Large Language Models Meet Graph Neural Networks: A Perspective of Graph MiningYuxin You0Zhen Liu1Xiangchao Wen2Yongtao Zhang3Wei Ai4School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China54th Research Institute of CETC, Shijiazhuang 050081, ChinaGraph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of graph neural networks (GNNs). However, GNNs are still deficient in generalizing to diverse graph data. Aiming to this issue, large language models (LLMs) could provide new solutions for graph mining tasks with their superior semantic understanding. In this review, we systematically review the combination and application techniques of LLMs and GNNs and present a novel taxonomy for research in this interdisciplinary field, which involves three main categories: GNN-driving-LLM(GdL), LLM-driving-GNN(LdG), and GNN-LLM-co-driving(GLcd). Within this framework, we reveal the capabilities of LLMs in enhancing graph feature extraction as well as improving the effectiveness of downstream tasks such as node classification, link prediction, and community detection. Although LLMs have demonstrated their great potential in handling graph-structured data, their high computational requirements and complexity remain challenges. Future research needs to continue to explore how to efficiently fuse LLMs and GNNs to achieve more powerful graph learning and reasoning capabilities and provide new impetus for the development of graph mining techniques.https://www.mdpi.com/2227-7390/13/7/1147graph mininglarge language modelsgraph neural networks |
| spellingShingle | Yuxin You Zhen Liu Xiangchao Wen Yongtao Zhang Wei Ai Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining Mathematics graph mining large language models graph neural networks |
| title | Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining |
| title_full | Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining |
| title_fullStr | Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining |
| title_full_unstemmed | Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining |
| title_short | Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining |
| title_sort | large language models meet graph neural networks a perspective of graph mining |
| topic | graph mining large language models graph neural networks |
| url | https://www.mdpi.com/2227-7390/13/7/1147 |
| work_keys_str_mv | AT yuxinyou largelanguagemodelsmeetgraphneuralnetworksaperspectiveofgraphmining AT zhenliu largelanguagemodelsmeetgraphneuralnetworksaperspectiveofgraphmining AT xiangchaowen largelanguagemodelsmeetgraphneuralnetworksaperspectiveofgraphmining AT yongtaozhang largelanguagemodelsmeetgraphneuralnetworksaperspectiveofgraphmining AT weiai largelanguagemodelsmeetgraphneuralnetworksaperspectiveofgraphmining |