Towards Graph Prompt Learning: A Survey and Beyond
Not on the map. Why?
Abstract (arXiv)
Large-scale "pre-train and prompt learning" paradigms have demonstrated remarkable adaptability, enabling broad applications across diverse domains such as question answering, image recognition, and multimodal retrieval. This approach fully leverages the potential of large-scale pre-trained models, reducing downstream data requirements and computational costs while enhancing model applicability across various tasks. Graphs, as versatile data structures that capture relationships between entities, play pivotal roles in fields such as social network analysis, recommender systems, and biological graphs. Despite the success of pre-train and prompt learning paradigms in Natural Language Processing (NLP) and Computer Vision (CV), their application in graph domains remains nascent. In graph-structured data, not only do the node and edge features often have disparate distributions, but the topological structures also differ significantly. This diversity in graph data can lead to incompatible patterns or gaps between pre-training and fine-tuning on downstream graphs. We aim to bridge this gap by summarizing methods for alleviating these disparities. This includes exploring prompt design methodologies, comparing related techniques, assessing application scenarios and datasets, and identifying unresolved problems and challenges. This survey categorizes over 100 relevant works in this field, summarizing general design principles and the latest applications, including text-attributed graphs, molecules, proteins, and recommendation systems. Through this extensive review, we provide a foundational understanding of graph prompt learning, aiming to impact not only the graph mining community but also the broader Artificial General Intelligence (AGI) community.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 78 of its 108 references that are in the map. First posted on arXiv 26 Aug 2024.
Builds on
78 of 108 references.
References · 78
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
38 more
- 2014DeepWalk: Online Learning of Social Representationscited by 1,543
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2020Graph Contrastive Learning with Augmentationscited by 1,203
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
- 2018Deep Graph Infomaxcited by 1,101
- 2019Strategies for Pre-training Graph Neural Networkscited by 964
- 2019Heterogeneous Graph Attention Networkcited by 732
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
- 2017Representation Learning on Graphs: Methods and Applicationscited by 456
- 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
- 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
- 2023Language is All a Graph Needscited by 219
- 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 209
- 2023GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarkingcited by 209
- 2023LLMRec: Large Language Models with Graph Augmentation for Recommendationcited by 171
- 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
- 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
- 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
- 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
- 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
- 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
- 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Modelcited by 105
- 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
- 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
- 2023PRODIGY: Enabling In-context Learning Over Graphscited by 97
- 2020Graph Meta Learning via Local Subgraphscited by 89
- 2023GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Textcited by 82
- 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
- 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
- 2024A Survey of Large Language Models for Graphscited by 71
- 2023GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learningcited by 70
- 2019Few-Shot Knowledge Graph Completioncited by 63
- 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
- 2022Does GNN Pretraining Help Molecular Representation?cited by 59
- 2022Graph-based Molecular Representation Learningcited by 51
- 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
- 2023HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learningcited by 45
- 2024BioRAG: A RAG-LLM Framework for Biological Question Reasoningcited by 42
50 most cited of 78 All 78 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.