RecFusion: A Binomial Diffusion Process for 1D Data for Recommendation
On the map: Diffusion models → Diffusion recommenders
Abstract (arXiv)
In this paper we propose RecFusion, which comprise a set of diffusion models for recommendation. Unlike image data which contain spatial correlations, a user-item interaction matrix, commonly utilized in recommendation, lacks spatial relationships between users and items. We formulate diffusion on a 1D vector and propose binomial diffusion, which explicitly models binary user-item interactions with a Bernoulli process. We show that RecFusion approaches the performance of complex VAE baselines on the core recommendation setting (top-n recommendation for binary non-sequential feedback) and the most common datasets (MovieLens and Netflix). Our proposed diffusion models that are specialized for 1D and/or binary setups have implications beyond recommendation systems, such as in the medical domain with MRI and CT scans.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Diffusion recommenders, one of 14 directions in Diffusion models. Builds on 39 of its 73 references that are in the map. First posted on arXiv 15 Jun 2023.
Builds on
39 of 73 references.
Closest ancestors · 1
Same direction, newest first
Other references · 38
- 2017Attention Is All You Needcited by 59,932
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2023Segment Anythingcited by 8,158
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2022Classifier-Free Diffusion Guidancecited by 5,717
- 2022Video Diffusion Modelscited by 2,280
- 2022Diffusion Models in Vision: A Surveycited by 1,008
- 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
- 2018Variational Autoencoders for Collaborative Filteringcited by 308
26 more
- 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 181
- 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
- 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
- 2019Learning Disentangled Representations for Recommendationcited by 110
- 2019Embarrassingly Shallow Autoencoders for Sparse Datacited by 93
- 2023Diffusion Recommender Modelcited by 87
- 2015Modeling User Exposure in Recommendationcited by 69
- 2019A Neural Influence Diffusion Model for Social Recommendationcited by 69
- 2019A Troubling Analysis of Reproducibility and Progress in Recommender Systems Researchcited by 65
- 2019RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedbackcited by 63
- 2019On the Difficulty of Evaluating Baselines: A Study on Recommender Systemscited by 46
- 2022Empowering Diffusion Models on the Embedding Space for Text Generationcited by 40
- 2018Evaluation of Session-based Recommendation Algorithmscited by 37
- 2022Blurring-Sharpening Process Models for Collaborative Filteringcited by 35
- 2019An Introductory Guide to Fano's Inequality with Applications in Statistical Estimationcited by 30
- 2023BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentationcited by 27
- 2020Modeling Personalized Item Frequency Information for Next-basket Recommendationcited by 24
- 2021Revisiting the Performance of iALS on Item Recommendation Benchmarkscited by 21
- 2022Infinite Recommendation Networks: A Data-Centric Approachcited by 20
- 2020Session-aware Recommendation: A Surprising Quest for the State-of-the-artcited by 15
- 2021A Next Basket Recommendation Reality Checkcited by 15
- 2021It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamiccited by 10
- 2018A Collective Variational Autoencoder for Top-N Recommendation with Side Informationcited by 9
- 2023Learning a Diffusion Prior for NeRFscited by 9
- 2020Alternating linear scheme in a Bayesian framework for low-rank tensor approximationcited by 3
- 2021Controllable Recommenders using Deep Generative Models and Disentanglementcited by 2
Built on by
Citing papers per year: 2024: 4; 2025: 2.
6 papers.
- 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
- 2024A Survey on Diffusion Models for Recommender Systemscited by 20
- 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendationcited by 6
- 2024S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domaincited by 5
- 2025Diffusion Models in Recommendation Systems: A Surveycited by 3
- 2025Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendationcited by 3
- 2025Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation30 Sep 2025
- 2025Diffusion Models in Recommendation Systems: A Survey17 Jan 2025
- 2024S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain31 Dec 2024
- 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendation17 Oct 2024
- 2024A Survey on Diffusion Models for Recommender Systems8 Sep 2024
- 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Data29 Apr 2024
Similar, not cited
Close in wording, no citation either way
- 2025Towards A Tri-View Diffusion Framework for Recommendation
- 2024RecDiff: Diffusion Model for Social Recommendation
- 2025Continuous-time Discrete-space Diffusion Model for Recommendation
- 2025Diffusion Recommender Models and the Illusion of Progress: A Concerning Study of Reproducibility and a Conceptual Mismatch
- 2023A novel diffusion recommendation algorithm based on multi-scale cnn and residual lstm ↗
- 2024Collaborative Filtering Based on Diffusion Models: Unveiling the Potential of High-Order Connectivity
- 2024Bridging User Dynamics: Transforming Sequential Recommendations with Schr"odinger Bridge and Diffusion Models
- 2026Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systems