Awesome
<h1 align="center"> Awesome-LLMs-in-Graph-tasks </a></h2> <h5 align="center"> If you like our project, please give us a star ⭐ on GitHub for the latest update.</h5> <h5 align="center"></h5>
This is a collection of papers on leveraging Large Language Models in Graph Tasks. It's based on our survey paper: A Survey of Graph Meets Large Language Model: Progress and Future Directions.
We will try to make this list updated frequently. If you found any error or any missed paper, please don't hesitate to open issues or pull requests.
Our survey has been accepted by IJCAI 2024 survey track.
How can LLMs help improve graph-related tasks?
With the help of LLMs, there has been a notable shift in the way we interact with graphs, particularly those containing nodes associated with text attributes. The integration of LLMs with traditional GNNs can be mutually beneficial and enhance graph learning. While GNNs are proficient at capturing structural information, they primarily rely on semantically constrained embeddings as node features, limiting their ability to express the full complexities of the nodes. Incorporating LLMs, GNNs can be enhanced with stronger node features that effectively capture both structural and contextual aspects. On the other hand, LLMs excel at encoding text but often struggle to capture structural information present in graph data. Combining GNNs with LLMs can leverage the robust textual understanding of LLMs while harnessing GNNs' ability to capture structural relationships, leading to more comprehensive and powerful graph learning.
<p align="center"><img src="Figures/overview.png" width=75% height=75%></p> <p align="center"><em>Figure 1.</em> The overview of Graph Meets LLMs.</p>Summarizations based on proposed taxonomy
<p align="center"><img src="Figures/summarization.png" width=100% height=75%></p> <p align="left"><em>Table 1.</em> A summary of models that leverage LLMs to assist graph-related tasks in literature, ordered by their release time. <b>Fine-tuning</b> denotes whether it is necessary to fine-tune the parameters of LLMs, and ♥ indicates that models employ parameter-efficient fine-tuning (PEFT) strategies, such as LoRA and prefix tuning. <b>Prompting</b> indicates the use of text-formatted prompts in LLMs, done manually or automatically. Acronyms in <b>Task</b>: Node refers to node-level tasks; Link refers to link-level tasks; Graph refers to graph-level tasks; Reasoning refers to Graph Reasoning; Retrieval refers to Graph-Text Retrieval; Captioning refers to Graph Captioning.</p >Table of Contents
LLM as Enhancer
-
(2022.03) [ICLR' 2022] Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [Paper | Code]
<details close> <summary>GIANT</summary> <p align="center"><img width="75%" src="Figures/GIANT.jpg" /></p> <p align="center"><em>The framework of GIANT.</em></p> </details> -
(2023.02) [ICLR' 2023] Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks [Paper | Code]
<details close> <summary>Edgeformers</summary> <p align="center"><img width="75%" src="Figures/Edgeformers.jpg" /></p> <p align="center"><em>The framework of Edgeformers.</em></p> </details> -
(2023.05) [KDD' 2023] Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications [Paper]
<details close> <summary>GALM</summary> <p align="center"><img width="75%" src="Figures/GALM.jpg" /></p> <p align="center"><em>The framework of GALM.</em></p> </details> -
(2023.06) [KDD' 2023] Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks [Paper | Code]
<details close> <summary>Heterformer</summary> <p align="center"><img width="75%" src="Figures/Heterformers.jpg" /></p> <p align="center"><em>The framework of Heterformer.</em></p> </details> -
(2023.05) [ICLR' 2024] Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning [Paper | Code]
<details close> <summary>TAPE</summary> <p align="center"><img width="75%" src="Figures/TAPE.jpg" /></p> <p align="center"><em>The framework of TAPE.</em></p> </details> -
(2023.08) [Arxiv' 2023] Exploring the potential of large language models (llms) in learning on graphs [Paper]
<details close> <summary>KEA</summary> <p align="center"><img width="75%" src="Figures/KEA.jpg" /></p> <p align="center"><em>The framework of KEA.</em></p> </details> -
(2023.07) [Arxiv' 2023] Can Large Language Models Empower Molecular Property Prediction? [Paper | Code]
<details close> <summary>LLM4Mol</summary> <p align="center"><img width="75%" src="Figures/LLM4Mol.jpg" /></p> <p align="center"><em>The framework of LLM4Mol.</em></p> </details> -
(2023.08) [Arxiv' 2023] Simteg: A frustratingly simple approach improves textual graph learning [Paper | Code]
<details close> <summary>SimTeG</summary> <p align="center"><img width="75%" src="Figures/SimTeG.jpg" /></p> <p align="center"><em>The framework of SimTeG.</em></p> </details> -
(2023.09) [Arxiv' 2023] Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs [Paper]
<details close> <summary>G-Prompt</summary> <p align="center"><img width="75%" src="Figures/G-Prompt.jpg" /></p> <p align="center"><em>The framework of G-Prompt.</em></p> </details> -
(2023.09) [Arxiv' 2023] TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning [Paper]
<details close> <summary>TouchUp-G</summary> <p align="center"><img width="75%" src="Figures/TouchUp-G.jpg" /></p> <p align="center"><em>The framework of TouchUp-G.</em></p> </details> -
(2023.09) [ICLR' 2024] One for All: Towards Training One Graph Model for All Classification Tasks [Paper | Code]
<details close> <summary>OFA</summary> <p align="center"><img width="75%" src="Figures/OFA.jpg" /></p> <p align="center"><em>The framework of OFA.</em></p> </details> -
(2023.10) [Arxiv' 2023] Learning Multiplex Embeddings on Text-rich Networks with One Text Encoder [Paper | Code]
<details close> <summary>METERN</summary> <p align="center"><img width="75%" src="Figures/METERN.jpg" /></p> <p align="center"><em>The framework of METERN.</em></p> </details> -
(2023.11) [WSDM' 2024] LLMRec: Large Language Models with Graph Augmentation for Recommendation [Paper | Code]
<details close> <summary>LLMRec</summary> <p align="center"><img width="75%" src="Figures/LLMRec.jpg" /></p> <p align="center"><em>The framework of LLMRec.</em></p> </details> -
(2023.11) [NeurIPS' 2023] WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding [Paper | Code]
<details close> <summary>WalkLM</summary> <p align="center"><img width="75%" src="Figures/WalkLM.jpg" /></p> <p align="center"><em>The framework of WalkLM.</em></p> </details> -
(2024.01) [IJCAI' 2024] Efficient Tuning and Inference for Large Language Models on Textual Graphs [Paper]
<details close> <summary>ENGINE</summary> <p align="center"><img width="75%" src="Figures/ENGINE.jpg" /></p> <p align="center"><em>The framework of ENGINE.</em></p> </details> -
(2024.02) [KDD' 2024] ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs [Paper]
<details close> <summary>ZeroG</summary> <p align="center"><img width="75%" src="Figures/ZeroG.jpg" /></p> <p align="center"><em>The framework of ZeroG.</em></p> </details> -
(2024.02) [Arxiv' 2024] UniGraph: Learning a Cross-Domain Graph Foundation Model From Natural Language [Paper]
<details close> <summary>UniGraph</summary> <p align="center"><img width="75%" src="Figures/UniGraph.jpg" /></p> <p align="center"><em>The framework of UniGraph.</em></p> </details> -
(2024.02) [CIKM' 2024] Distilling Large Language Models for Text-Attributed Graph Learning [Paper]
<details close> <summary>Pan, et al.</summary> <p align="center"><img width="75%" src="Figures/Pan_etal.jpg" /></p> <p align="center"><em>The framework of Pan, et al.</em></p> </details> -
(2024.10) [CIKM' 2024] When LLM Meets Hypergraph: A Sociological Analysis on Personality via Online Social Networks [Paper | Code]
<details close> <summary>Shu, et al.</summary> <p align="center"><img width="75%" src="Figures/shu2024llm.jpg" /></p> <p align="center"><em>The framework of Shu, et al.</em></p> </details>
LLM as Predictor
-
(2023.05) [NeurIPS' 2023] Can language models solve graph problems in natural language? [Paper | Code]
<details close> <summary>NLGraph</summary> <p align="center"><img width="75%" src="Figures/NLGraph.jpg" /></p> <p align="center"><em>The framework of NLGraph.</em></p> </details> -
(2023.05) [Arxiv' 2023] GPT4Graph: Can Large Language Models Understand Graph Structured Data? An Empirical Evaluation and Benchmarking [Paper | Code]
<details close> <summary>GPT4Graph</summary> <p align="center"><img width="75%" src="Figures/GPT4Graph.png" /></p> <p align="center"><em>The framework of GPT4Graph.</em></p> </details> -
(2023.06) [NeurIPS' 2023] GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning [Paper | Code]
<details close> <summary>GIMLET</summary> <p align="center"><img width="75%" src="Figures/GIMLET.jpg" /></p> <p align="center"><em>The framework of GIMLET.</em></p> </details> -
(2023.07) [Arxiv' 2023] Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs [Paper | Code]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Chen et al.jpg" /></p> <p align="center"><em>The designed prompts of Chen et al.</em></p> </details> -
(2023.08) [Arxiv' 2023] GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text [Paper]
<details close> <summary>GIT-Mol</summary> <p align="center"><img width="75%" src="Figures/GIT-Mol.jpg" /></p> <p align="center"><em>The framework of GIT-Mol.</em></p> </details> -
(2023.08) [Arxiv' 2023] Natural Language is All a Graph Needs [Paper | Code]
<details close> <summary>InstructGLM</summary> <p align="center"><img width="75%" src="Figures/InstructGLM.jpg" /></p> <p align="center"><em>The framework of InstructGLM.</em></p> </details> -
(2023.08) [Arxiv' 2023] Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis [Paper | Code]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Liu et al.jpg" /></p> <p align="center"><em>The designed prompts of Liu et al.</em></p> </details> -
(2023.09) [Arxiv' 2023] Can LLMs Effectively Leverage Graph Structural Information: When and Why [Paper | Code]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Huang et al.jpg" /></p> <p align="center"><em>The designed prompts of Huang et al.</em></p> </details> -
(2023.10) [Arxiv' 2023] GraphText: Graph Reasoning in Text Space [Paper] | Code]
<details close> <summary>GraphText</summary> <p align="center"><img width="75%" src="Figures/GraphText.jpg" /></p> <p align="center"><em>The framework of GraphText.</em></p> </details> -
(2023.10) [Arxiv' 2023] Talk like a Graph: Encoding Graphs for Large Language Models [Paper]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Fatemi et al.jpg" /></p> <p align="center"><em>The designed prompts of Fatemi et al.</em></p> </details> -
(2023.10) [Arxiv' 2023] GraphLLM: Boosting Graph Reasoning Ability of Large Language Model [Paper | Code]
<details close> <summary>GraphLLM</summary> <p align="center"><img width="75%" src="Figures/GraphLLM.jpg" /></p> <p align="center"><em>The framework of GraphLLM.</em></p> </details> -
(2023.10) [Arxiv' 2023] Beyond Text: A Deep Dive into Large Language Model [Paper]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Hu et al.jpg" /></p> <p align="center"><em>The designed prompts of Hu et al.</em></p> </details> -
(2023.10) [EMNLP' 2023] MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter [Paper | Code]
<details close> <summary>MolCA</summary> <p align="center"><img width="75%" src="Figures/MolCA.jpg" /></p> <p align="center"><em>The framework of MolCA.</em></p> </details> -
(2023.10) [Arxiv' 2023] GraphGPT: Graph Instruction Tuning for Large Language Models [Paper | Code]
<details close> <summary>GraphGPT</summary> <p align="center"><img width="75%" src="Figures/GraphGPT.jpg" /></p> <p align="center"><em>The framework of GraphGPT.</em></p> </details> -
(2023.10) [EMNLP' 2023] ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction [Paper | Code]
<details close> <summary>ReLM</summary> <p align="center"><img width="75%" src="Figures/ReLM.jpg" /></p> <p align="center"><em>The framework of ReLM.</em></p> </details> -
(2023.10) [Arxiv' 2023] LLM4DyG: Can Large Language Models Solve Problems on Dynamic Graphs? [Paper]
<details close> <summary>LLM4DyG</summary> <p align="center"><img width="75%" src="Figures/LLM4DyG.jpg" /></p> <p align="center"><em>The framework of LLM4DyG.</em></p> </details> -
(2023.10) [Arxiv' 2023] Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs [Paper]
<details close> <summary>DGTL</summary> <p align="center"><img width="75%" src="Figures/DGTL.jpg" /></p> <p align="center"><em>The framework of DGTL.</em></p> </details> -
(2023.11) [Arxiv' 2023] Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models [Paper]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Das et al.jpg" /></p> <p align="center"><em>The framework of Das et al.</em></p> </details> -
(2023.11) [Arxiv' 2023] InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery [Paper]
<details close> <summary>InstructMol</summary> <p align="center"><img width="75%" src="Figures/InstructMol.jpg" /></p> <p align="center"><em>The framework of InstructMol.</em></p> </details> -
(2023.12) [Arxiv' 2023] When Graph Data Meets Multimodal: A New Paradigm for Graph Understanding and Reasoning [Paper]
<details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Ai et al.jpg" /></p> <p align="center"><em>The framework of Ai et al.</em></p> </details> -
(2024.02) [Arxiv' 2024] Let Your Graph Do the Talking: Encoding Structured Data for LLMs [Paper]
<details close> <summary>GraphToken</summary> <p align="center"><img width="75%" src="Figures/GraphToken.jpg" /></p> <p align="center"><em>The framework of GraphToken.</em></p> </details> -
(2024.02) [Arxiv' 2024] Rendering Graphs for Graph Reasoning in Multimodal Large Language Models [Paper]
<details close> <summary>GITA</summary> <p align="center"><img width="75%" src="Figures/GITA.jpg" /></p> <p align="center"><em>The framework of GITA.</em></p> </details> -
(2024.02) [WWW' 2024] GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks [Paper | Code]
<details close> <summary>GraphTranslator</summary> <p align="center"><img width="75%" src="Figures/GraphTranslator.jpg" /></p> <p align="center"><em>The framework of GraphTranslator.</em></p> </details> -
(2024.02) [Arxiv' 2024] InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment [Paper | Code]
<details close> <summary>InstructGraph</summary> <p align="center"><img width="75%" src="Figures/InstructGraph.jpg" /></p> <p align="center"><em>The framework of InstructGraph.</em></p> </details> -
(2024.02) [Arxiv' 2024] LLaGA: Large Language and Graph Assistant [Paper | Code]
<details close> <summary>LLaGA</summary> <p align="center"><img width="75%" src="Figures/LLaGA.jpg" /></p> <p align="center"><em>The framework of LLaGA.</em></p> </details> -
(2024.02) [WWW' 2024] Can GNN be Good Adapter for LLMs? [Paper]
<details close> <summary>GraphAdapter</summary> <p align="center"><img width="75%" src="Figures/graphadapter.jpg" /></p> <p align="center"><em>The framework of GraphAdapter.</em></p> </details> -
(2024.02) [Arxiv' 2024] HiGPT: Heterogeneous Graph Language Model [Paper | Code]
<details close> <summary>HiGPT</summary> <p align="center"><img width="75%" src="Figures/HiGPT.jpg" /></p> <p align="center"><em>The framework of HiGPT.</em></p> </details> -
(2024.02) [Arxiv' 2024] GraphWiz: An Instruction-Following Language Model for Graph Problems [Paper | Code]
<details close> <summary>GraphWiz</summary> <p align="center"><img width="75%" src="Figures/GraphWiz.jpg" /></p> <p align="center"><em>The framework of GraphWiz.</em></p> </details> -
(2024.03) [Arxiv' 2024] OpenGraph: Towards Open Graph Foundation Models [Paper | Code]
<details close> <summary>OpenGraph</summary> <p align="center"><img width="75%" src="Figures/OpenGraph.jpg" /></p> <p align="center"><em>The framework of OpenGraph.</em></p> </details> -
(2024.07) [Arxiv' 2024] GOFA: A Generative One-For-All Model for Joint Graph Language Modeling [Paper | Code]
<details close> <summary>GOFA</summary> <p align="center"><img width="75%" src="Figures/GOFA.jpg" /></p> <p align="center"><em>The framework of GOFA.</em></p> </details>
GNN-LLM Alignment
- (2020.08) [Arxiv' 2020] Graph-based Modeling of Online Communities for Fake News Detection [Paper | Code] <details close> <summary>SAFER</summary> <p align="center"><img width="75%" src="Figures/SAFER.jpg" /></p> <p align="center"><em>The framework of SAFER.</em></p> </details>
- (2021.05) [NeurIPS' 2021] GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph [Paper | Code] <details close> <summary>GraphFormers</summary> <p align="center"><img width="75%" src="Figures/GraphFormers.jpg" /></p> <p align="center"><em>The framework of GraphFormers.</em></p> </details>
- (2021.11) [EMNLP' 2021] Text2Mol: Cross-Modal Molecule Retrieval with Natural Language Queries [Paper | Code] <details close> <summary>Text2Mol</summary> <p align="center"><img width="75%" src="Figures/Text2Mol.jpg" /></p> <p align="center"><em>The framework of Text2Mol.</em></p> </details>
- (2022.07) [ACL' 2023] Hidden Schema Networks [Paper | Code] <details close> <summary>HSN</summary> <p align="center"><img width="75%" src="Figures/HSN.png" /></p> <p align="center"><em>The framework of HSN.</em></p> </details>
- (2022.09) [Arxiv' 2022] A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language [Paper | Code] <details close> <summary>MoMu</summary> <p align="center"><img width="75%" src="Figures/MoMu.jpg" /></p> <p align="center"><em>The framework of MoMu.</em></p> </details>
- (2022.10) [ICLR' 2023] Learning on Large-scale Text-attributed Graphs via Variational Inference [Paper | Code] <details close> <summary>GLEM</summary> <p align="center"><img width="75%" src="Figures/GLEM.jpg" /></p> <p align="center"><em>The framework of GLEM.</em></p> </details>
- (2022.12) [NMI' 2023] Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval [Paper | Code] <details close> <summary>MoleculeSTM</summary> <p align="center"><img width="75%" src="Figures/MoleculeSTM.jpg" /></p> <p align="center"><em>The framework of MoleculeSTM.</em></p> </details>
- (2023.04) [Arxiv' 2023] Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs [Paper | Code] <details close> <summary>GRAD</summary> <p align="center"><img width="75%" src="Figures/GRAD.jpg" /></p> <p align="center"><em>The framework of GRAD.</em></p> </details>
- (2023.05) [ACL' 2023] PATTON : Language Model Pretraining on Text-Rich Networks [Paper | Code] <details close> <summary>Patton</summary> <p align="center"><img width="75%" src="Figures/Patton.jpg" /></p> <p align="center"><em>The framework of Patton.</em></p> </details>
- (2023.05) [Arxiv' 2023] ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings [Paper | Code] <details close> <summary>ConGraT</summary> <p align="center"><img width="75%" src="Figures/ConGraT.jpg" /></p> <p align="center"><em>The framework of ConGraT.</em></p> </details>
- (2023.07) [Arxiv' 2023] Prompt Tuning on Graph-augmented Low-resource Text Classification [Paper | Code] <details close> <summary>G2P2</summary> <p align="center"><img width="75%" src="Figures/G2P2.jpg" /></p> <p align="center"><em>The framework of G2P2.</em></p> </details>
- (2023.10) [EMNLP' 2023] GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs [Paper | Code] <details close> <summary>GRENADE</summary> <p align="center"><img width="75%" src="Figures/GRENADE.jpg" /></p> <p align="center"><em>The framework of GRENADE.</em></p> </details>
- (2023.10) [WWW' 2024] Representation Learning with Large Language Models for Recommendation [Paper | Code] <details close> <summary>RLMRec</summary> <p align="center"><img width="75%" src="Figures/RLMRec.jpg" /></p> <p align="center"><em>The framework of RLMRec.</em></p> </details>
- (2023.10) [EMNLP' 2023] Pretraining Language Models with Text-Attributed Heterogeneous Graphs [Paper | Code] <details close> <summary>THLM</summary> <p align="center"><img width="75%" src="Figures/THLM.jpg" /></p> <p align="center"><em>The framework of THLM.</em></p> </details>
Benchmarks
-
(2024.07) [NeurIPS' 2024] GLBench: A Comprehensive Benchmark for Graph with Large Language Models [Paper | Code]
-
(2024.05) [NeurIPS' 2024] TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs [Paper][Code]
Others
LLM as Annotator
-
(2023.10) [ICLR' 2024] Label-free Node Classification on Graphs with Large Language Models (LLMs) [Paper | Code]
<details close> <summary>LLM-GNN</summary> <p align="center"><img width="75%" src="Figures/LLM-GNN.png" /></p> <p align="center"><em>The framework of LLM-GNN.</em></p> </details> -
(2024.09) [NeurIPS' 2024] Entity Alignment with Noisy Annotations from Large Language Models [Paper | Code]
<details close> <summary>LLM4EA</summary> <p align="center"><img width="75%" src="Figures/LLM4EA.jpg" /></p> <p align="center"><em>The framework of LLM4EA.</em></p> </details>
LLM as Controller
- (2023.10) [Arxiv' 2023] Graph Neural Architecture Search with GPT-4 [Paper] <details close> <summary>GPT4GNAS</summary> <p align="center"><img width="75%" src="Figures/GPT4GNAS.jpg" /></p> <p align="center"><em>The framework of GPT4GNAS.</em></p> </details>
LLM as Sample Generator
- (2023.10) [Arxiv' 2023] Empower Text-Attributed Graphs Learning with Large Language Models (LLMs) [Paper] <details close> <summary>ENG</summary> <p align="center"><img width="75%" src="Figures/ENG.jpg" /></p> <p align="center"><em>The framework of ENG.</em></p> </details>
LLM as Similarity Analyzer
- (2023.11) [Arxiv' 2023] Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs [Paper] <details close> <summary>Framework</summary> <p align="center"><img width="75%" src="Figures/Sun et al.jpg" /></p> <p align="center"><em>The framework of Sun et al.</em></p> </details>
LLM for Robustness
-
(2024.05) [Arxiv' 2024] Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level [Paper]
<details close> <summary>Lei, et al.</summary> <p align="center"><img width="75%" src="Figures/Lei, et al.jpg" /></p> <p align="center"><em>The framework of Lei, et al..</em></p> </details> -
(2024.08) [Arxiv' 2024] Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks? [Paper]
<details close> <summary>LLM4RGNN</summary> <p align="center"><img width="75%" src="Figures/LLM4RGNN.jpg" /></p> <p align="center"><em>The framework of LLM4RGNN.</em></p> </details>
LLM for Task Planning
- (2024.05) [NeurIPS' 2024] Can Graph Learning Improve Planning in LLM-based Agents? [Paper | Code] <details close> <summary>GNN4TaskPlan</summary> <p align="center"><img width="75%" src="Figures/GNN4TaskPlan.jpg" /></p> <p align="center"><em>The definition of task planning and the proposed framework.</em></p> </details>
Other Repos
We note that several repos also summarize papers on the integration of LLMs and graphs. However, we differentiate ourselves by organizing these papers leveraging a new and more granular taxonomy. We recommend researchers to explore some repositories for a comprehensive survey.
-
Awesome-Graph-LLM, created by Xiaoxin He from NUS.
-
Awesome-Large-Graph-Model, created by Ziwei Zhang from THU.
-
Awesome-Language-Model-on-Graphs, created by Bowen Jin from UIUC.
We highly recommend a repository that summarizes the work on Graph Prompt, which is very close to Graph-LLM.
- Awesome-Graph-Prompt, created by Xixi Wu from CUHK.
Contributing
If you have come across relevant resources, feel free to open an issue or submit a pull request.
* (_time_) [conference] **paper_name** [[Paper](link) | [Code](link)]
<details close>
<summary>Model name</summary>
<p align="center"><img width="75%" src="Figures/xxx.jpg" /></p>
<p align="center"><em>The framework of model name.</em></p>
</details>
Cite Us
Feel free to cite this work if you find it useful to you!
@article{li2023survey,
title={A Survey of Graph Meets Large Language Model: Progress and Future Directions},
author={Li, Yuhan and Li, Zhixun and Wang, Peisong and Li, Jia and Sun, Xiangguo and Cheng, Hong and Yu, Jeffrey Xu},
journal={arXiv preprint arXiv:2311.12399},
year={2023}
}