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

Abstract

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 $\beta$ hyperparameter for the $\beta$-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.

In The Thirteenth ACM International Conference on Web Search and Data Mining (WSDM '20), February 3-7, 2020, Houston, TX, USA. ACM, New York, NY, USA, 9 pages

Cited by in corpus (20)

• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Learning Robust Recommenders through Cross-Model Agreement
• RecDCL: Dual Contrastive Learning for Recommendation
• Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction
• Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
• Contemporary Recommendation Systems on Big Data and Their Applications: A Survey
• Personality-Driven Social Multimedia Content Recommendation
• Mutually-Regularized Dual Collaborative Variational Auto-encoder for Recommendation Systems
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation
• Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
• Content-Based Collaborative Generation for Recommender Systems
• Collaborative Residual Metric Learning
• Cyberswarm: a novel swarm intelligence algorithm inspired by cyber community dynamics
• Improved Estimation of Ranks for Learning Item Recommenders with Negative Sampling
• The Hidden Cost of Defaults in Recommender System Evaluation
• Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
• MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
• Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders
• Scalable Personalised Item Ranking through Parametric Density Estimation