mlsanityData to 13 Oct 2026

GraphPro: Graph Pre-training and Prompt Learning for Recommendation

arXiv 2311.16716 ↗First posted 28 Nov 2023cs.IR cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

GNN-based recommenders have excelled in modeling intricate user-item interactions through multi-hop message passing. However, existing methods often overlook the dynamic nature of evolving user-item interactions, which impedes the adaption to changing user preferences and distribution shifts in newly arriving data. Thus, their scalability and performances in real-world dynamic environments are limited. In this study, we propose GraphPro, a framework that incorporates parameter-efficient and dynamic graph pre-training with prompt learning. This novel combination empowers GNNs to effectively capture both long-term user preferences and short-term behavior dynamics, enabling the delivery of accurate and timely recommendations. Our GraphPro framework addresses the challenge of evolving user preferences by seamlessly integrating a temporal prompt mechanism and a graph-structural prompt learning mechanism into the pre-trained GNN model. The temporal prompt mechanism encodes time information on user-item interaction, allowing the model to naturally capture temporal context, while the graph-structural prompt learning mechanism enables the transfer of pre-trained knowledge to adapt to behavior dynamics without the need for continuous incremental training. We further bring in a dynamic evaluation setting for recommendation to mimic real-world dynamic scenarios and bridge the offline-online gap to a better level. Our extensive experiments including a large-scale industrial deployment showcases the lightweight plug-in scalability of our GraphPro when integrated with various state-of-the-art recommenders, emphasizing the advantages of GraphPro in terms of effectiveness, robustness and efficiency. The implementation details and source code of our GraphPro are available in the repository at https://github.com/HKUDS/GraphPro

Key facts. Cited by 17 papers in the map (data through 13 Oct 2026). Builds on 45 of its 61 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

45 of 61 references.

References · 45

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,712
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,628
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,207
  5. 2018Self-Attentive Sequential Recommendationcited by 1,175
  6. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,135
  7. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,135
  8. 2017Neural Collaborative Filteringcited by 1,110
  9. 2018Deep Graph Infomaxcited by 1,104
  10. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,093
  11. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 958
  12. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 935
33 more
  1. 2019Neural Graph Collaborative Filteringcited by 660
  2. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 446
  3. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 445
  4. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  5. 2020S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximizationcited by 311
  6. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
  7. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  8. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  9. 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
  10. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  11. 2020Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approachcited by 119
  12. 2021Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendationcited by 101
  13. 2022Self-Supervised Learning for Recommender Systems: A Surveycited by 95
  14. 2022Intent Contrastive Learning for Sequential Recommendationcited by 90
  15. 2021Sequential Recommendation with Graph Neural Networkscited by 89
  16. 2018dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learningcited by 88
  17. 2021UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendationcited by 87
  18. 2017Dynamic Graph Convolutional Networkscited by 83
  19. 2023LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendationcited by 72
  20. 2021How Powerful is Graph Convolution for Recommendation?cited by 50
  21. 2020Pre-Training Graph Neural Networks for Cold-Start Users and Items Representationcited by 42
  22. 2022Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendationcited by 42
  23. 2020A Critical Study on Data Leakage in Recommender System Offline Evaluationcited by 38
  24. 2023Debiased Contrastive Learning for Sequential Recommendationcited by 38
  25. 2022Sequential Recommendation via Stochastic Self-Attentioncited by 37
  26. 2023Automated Self-Supervised Learning for Recommendationcited by 37
  27. 2021Dynamic Graph Collaborative Filteringcited by 33
  28. 2022Disentangled Contrastive Learning for Social Recommendationcited by 27
  29. 2022A Review-aware Graph Contrastive Learning Framework for Recommendationcited by 18
  30. 2021RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendationcited by 15
  31. 2019Sequential Recommendation with Dual Side Neighbor-based Collaborative Relation Modelingcited by 11
  32. 2021Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendationcited by 5
  33. 2023Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filteringcited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 9; 2025: 7; 2026: 1.

17 papers.

Sort:

By area:

  1. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 76
  2. 2024ProG: A Graph Prompt Learning Benchmarkcited by 29
  3. 2025GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuningcited by 13
  4. 2024Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysiscited by 10
  5. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  6. 2024Urban Region Pre-training and Prompting: A Graph-based Approachcited by 8
  7. 2024A Comprehensive Survey on Self-Supervised Learning for Recommendationcited by 6
  8. 2024Backdoor Graph Condensationcited by 5
  9. 2024Graph Augmentation for Recommendationcited by 4
  10. 2025Graph Prompting for Graph Learning Models: Recent Advances and Future Directionscited by 3
  11. 2025A Scalable and Efficient Signal Integration System for Job Matchingcited by 2
  12. 2025Ultra Fast Warm Start Solution for Graph Recommendationscited by 2
5 more
  1. 2025Simple yet Effective Node Property Prediction on Edge Streams under Distribution Shiftscited by 1
  2. 2024Fusion Matrix Prompt Enhanced Self-Attention Spatial-Temporal Interactive Traffic Forecasting Frameworkcited by 0
  3. 2025CORONA: A Coarse-to-Fine Framework for Graph-based Recommendation with Large Language Modelscited by 0
  4. 2025Odin: Oriented Dual-module Integration for Text-rich Network Representation Learningcited by 0
  5. 2026A Cross-graph Tuning-free GNN Prompting Frameworkcited by 0