Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
RecVAE : A new variational autoencoder for top-n recommendations with implicit feedback. / Shenbin, Ilya; Alekseev, Anton; Tutubalina, Elena; Malykh, Valentin; Nikolenko, Sergey I.
WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining. Association for Computing Machinery, 2020. p. 528-536 (WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - RecVAE
T2 - 13th ACM International Conference on Web Search and Data Mining, WSDM 2020
AU - Shenbin, Ilya
AU - Alekseev, Anton
AU - Tutubalina, Elena
AU - Malykh, Valentin
AU - Nikolenko, Sergey I.
N1 - Publisher Copyright: © 2020 Copyright held by the owner/author(s).
PY - 2020/1/20
Y1 - 2020/1/20
N2 - 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.
AB - 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.
KW - Collaborative filtering
KW - Deep learning
KW - Variational autoencoders
UR - http://www.scopus.com/inward/record.url?scp=85079538827&partnerID=8YFLogxK
U2 - 10.1145/3336191.3371831
DO - 10.1145/3336191.3371831
M3 - Conference contribution
AN - SCOPUS:85079538827
T3 - WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining
SP - 528
EP - 536
BT - WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining
PB - Association for Computing Machinery
Y2 - 3 February 2020 through 7 February 2020
ER -
ID: 95169019