mlsanityData to 7 Oct 2026

A Diffusion model for POI recommendation

arXiv 2304.07041 ↗First posted 14 Apr 2023cs.IRcited by 24

On the map: Diffusion models → Diffusion recommenders

Abstract (arXiv)

Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user's next destination. Previous works on POI recommendation have laid focused on modeling the user's spatial preference. However, existing works that leverage spatial information are only based on the aggregation of users' previous visited positions, which discourages the model from recommending POIs in novel areas. This trait of position-based methods will harm the model's performance in many situations. Additionally, incorporating sequential information into the user's spatial preference remains a challenge. In this paper, we propose Diff-POI: a Diffusion-based model that samples the user's spatial preference for the next POI recommendation. Inspired by the wide application of diffusion algorithm in sampling from distributions, Diff-POI encodes the user's visiting sequence and spatial character with two tailor-designed graph encoding modules, followed by a diffusion-based sampling strategy to explore the user's spatial visiting trends. We leverage the diffusion process and its reversed form to sample from the posterior distribution and optimized the corresponding score function. We design a joint training and inference framework to optimize and evaluate the proposed Diff-POI. Extensive experiments on four real-world POI recommendation datasets demonstrate the superiority of our Diff-POI over state-of-the-art baseline methods. Further ablation and parameter studies on Diff-POI reveal the functionality and effectiveness of the proposed diffusion-based sampling strategy for addressing the limitations of existing methods.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in Diffusion recommenders, one of 14 directions in Diffusion models. Builds on 30 of its 72 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

30 of 72 references.

References · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  10. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  11. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  12. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 952
18 more
  1. 2015Session-based Recommendations with Recurrent Neural Networkscited by 685
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  3. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  4. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  5. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  6. 2016Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendationcited by 152
  7. 2020Structural Deep Clustering Networkcited by 145
  8. 2020Disentangled Graph Collaborative Filteringcited by 118
  9. 2021STAN: Spatio-Temporal Attention Network for Next Location Recommendationcited by 102
  10. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  11. 2023GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendationcited by 57
  12. 2020STP-UDGAT: Spatial-Temporal-Preference User Dimensional Graph Attention Network for Next POI Recommendationcited by 31
  13. 2020GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendationcited by 24
  14. 2022GLCC: A General Framework for Graph-Level Clusteringcited by 21
  15. 2021Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentationcited by 20
  16. 2022DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendationcited by 9
  17. 2022Kernel-based Substructure Exploration for Next POI Recommendationcited by 8
  18. 2022Empowering Next POI Recommendation with Multi-Relational Modelingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 10; 2026: 4.

24 papers.

Sort:

By area:

  1. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  2. 2024A Survey on Diffusion Models for Recommender Systemscited by 20
  3. 2024A Survey of Generative Techniques for Spatial-Temporal Data Miningcited by 14
  4. 2024A Survey on Point-of-Interest Recommendation: Models, Architectures, and Securitycited by 12
  5. 2024Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendationcited by 11
  6. 2024Taming the Long Tail in Human Mobility Predictioncited by 8
  7. 2025Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion Modelcited by 7
  8. 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendationcited by 6
  9. 2024How Fair is Your Diffusion Recommender Model?cited by 5
  10. 2025Diffusion Models in Recommendation Systems: A Surveycited by 3
  11. 2025Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarkscited by 3
  12. 2025Adaptive Location Hierarchy Learning for Long-Tailed Mobility Predictioncited by 3
12 more
  1. 2024Diffusion-based Graph Generative Methodscited by 2
  2. 2026TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generationcited by 2
  3. 2024GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Poolingcited by 1
  4. 2025Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendationcited by 1
  5. 2025Leveraging Multimodal Data and Side Users for Diffusion Cross-Domain Recommendationcited by 0
  6. 2025SEQ-GPT: LLM-assisted Spatial Query via Examplecited by 0
  7. 2025STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction over Human Trajectory Datacited by 0
  8. 2025Fine-Tuning Diffusion-Based Recommender Systems via Reinforcement Learning with Reward Function Optimizationcited by 0
  9. 2025Learning Multi-Modal Mobility Dynamics for Generalized Next Location Recommendationcited by 0
  10. 2026EviRec: Continual Evidence Learning for Dual Cold-Start POI Recommendationcited by 0
  11. 2026Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systemscited by 0
  12. 2026FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Give the Long-tail More SPACE: Promoting Provider Fairness in Next POI Recommendation ↗
  2. 2026ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
  3. 2026An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark
  4. 2025TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation
  5. 2025RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking
  6. 2026Think2Go: Generative Next POI Recommendation with LLM Reasoning
  7. 2025Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction
  8. 2025Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual Mismatch