mlsanityData to 14 Oct 2026

RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback

arXiv 1912.11160 ↗First posted 24 Dec 2019cs.IR cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

Recent research has shown the advantages of using autoencoders based on deep neural networks for collaborative filtering. In particular, the recently proposed Mult-VAE model, which used the multinomial likelihood variational autoencoders, has shown excellent results for top-N recommendations. In this work, we propose the Recommender VAE (RecVAE) model that originates from our research on regularization techniques for variational autoencoders. RecVAE introduces several novel ideas to improve Mult-VAE, including a novel composite prior distribution for the latent codes, a new approach to setting the β hyperparameter for the β-VAE framework, and a new approach to training based on alternating updates. In experimental evaluation, we show that RecVAE significantly outperforms previously proposed autoencoder-based models, including Mult-VAE and RaCT, across classical collaborative filtering datasets, and present a detailed ablation study to assess our new developments. Code and models are available at https://github.com/ilya-shenbin/RecVAE.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 7; 2023: 5; 2024: 20; 2025: 11; 2026: 5.

63 papers.

Sort:

By area:

  1. 2021SimpleX: A Simple and Strong Baseline for Collaborative Filteringcited by 65
  2. 2021Adversarial and Contrastive Variational Autoencoder for Sequential Recommendationcited by 28
  3. 2021Revisiting the Performance of iALS on Item Recommendation Benchmarkscited by 21
  4. 2022DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluationcited by 19
  5. 2022ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendationcited by 19
  6. 2024Collaborative Filtering Based on Diffusion Models: Unveiling the Potential of High-Order Connectivitycited by 18
  7. 2021Learning Robust Recommenders through Cross-Model Agreementcited by 15
  8. 2022Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Frameworkcited by 13
  9. 2025Multimodal Quantitative Language for Generative Recommendationcited by 12
  10. 2024RecDCL: Dual Contrastive Learning for Recommendationcited by 11
  11. 2021Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Ratescited by 10
  12. 2024A Directional Diffusion Graph Transformer for Recommendationcited by 9
38 more
  1. 2024Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approachcited by 9
  2. 2021Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filteringcited by 8
  3. 2023Toward a Better Understanding of Loss Functions for Collaborative Filteringcited by 8
  4. 2024RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendationcited by 8
  5. 2024CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systemscited by 8
  6. 2025Flow Matching for Collaborative Filteringcited by 8
  7. 2021Denoising User-aware Memory Network for Recommendationcited by 7
  8. 2023It's Enough: Relaxing Diagonal Constraints in Linear Autoencoders for Recommendationcited by 7
  9. 2023RecFusion: A Binomial Diffusion Process for 1D Data for Recommendationcited by 7
  10. 2022Personality-Driven Social Multimedia Content Recommendationcited by 6
  11. 2024A Comprehensive Survey on Self-Supervised Learning for Recommendationcited by 6
  12. 2025Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendationcited by 6
  13. 2021Local Collaborative Autoencoderscited by 5
  14. 2024How Fair is Your Diffusion Recommender Model?cited by 5
  15. 2024Algorithmic Drift: A Simulation Framework to Study the Effects of Recommender Systems on User Preferencescited by 5
  16. 2021One Backward from Ten Forward, Subsampling for Large-Scale Deep Learningcited by 4
  17. 2024SVD-AE: Simple Autoencoders for Collaborative Filteringcited by 4
  18. 2021Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)cited by 3
  19. 2022Bilateral Self-unbiased Learning from Biased Implicit Feedbackcited by 3
  20. 2024Diffusion Cross-domain Recommendationcited by 3
  21. 2024GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendationcited by 3
  22. 2024A Survey on Deep Neural Networks in Collaborative Filtering Recommendation Systemscited by 3
  23. 2025Fidelity-Aware Recommendation Explanations via Stochastic Path Integrationcited by 3
  24. 2024MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommendercited by 2
  25. 2021On the Regularization of Autoencoderscited by 1
  26. 2022REST: Debiased Social Recommendation via Reconstructing Exposure Strategiescited by 1
  27. 2023Causal Structure Representation Learning of Confounders in Latent Space for Recommendationcited by 1
  28. 2024Geometric Collaborative Filtering with Convergencecited by 1
  29. 2024A Case Study of Next Portfolio Prediction for Mutual Fundscited by 1
  30. 2025Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systemscited by 1
  31. 2025M^2VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendationcited by 1
  32. 2026Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filteringcited by 1
  33. 2021Scalable Personalised Item Ranking through Parametric Density Estimationcited by 0
  34. 2021A Comprehensive Review on Non-Neural Networks Collaborative Filtering Recommendation Systemscited by 0
  35. 2021Deep Variational Models for Collaborative Filtering-based Recommender Systemscited by 0
  36. 2021Next Period Recommendation Reality Checkcited by 0
  37. 2022Multi-stage Ensemble Model for Cross-market Recommendationcited by 0
  38. 2023Label Denoising through Cross-Model Agreementcited by 0

50 most cited of 63 All 63 (JSON)