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

24 Dec 2019  Â·  Ilya Shenbin, Anton Alekseev, Elena Tutubalina, Valentin Malykh, Sergey I. Nikolenko ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Recommendation Systems Million Song Dataset RecVAE Recall@20 0.276 # 3
Recall@50 0.374 # 3
nDCG@100 0.326 # 3
Recommendation Systems MovieLens 20M RecVAE Recall@20 0.414 # 2
Recall@50 0.553 # 1
nDCG@100 0.442 # 3
Recommendation Systems Netflix RecVAE Recall@20 0.361 # 3
Recall@50 0.452 # 2
nDCG@100 0.394 # 2

Methods