Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

3-2021

Abstract

Preference data is a form of dyadic data, with measurements associated with pairs of elements arising from two discrete sets of objects. These are users and items, as well as their interactions, e.g., ratings. We are interested in learning representations for both sets of objects, i.e., users and items, to predict unknown pairwise interactions. Motivated by the recent successes of deep latent variable models, we propose Bilateral Variational Autoencoder (BiVAE), which arises from a combination of a generative model of dyadic data with two inference models, user- and item-based, parameterized by neural networks. Interestingly, our model can take the form of a Bayesian variational autoencoder either on the user or item side. As opposed to the vanilla VAE model, BiVAE is "bilateral'', in that users and items are treated similarly, making it more apt for two-way or dyadic data. While theoretically sound, we formally show that, similarly to VAE, our model might suffer from an over-regularized latent space. This issue, known as posterior collapse in the VAE literature, may appear due to assuming an over-simplified prior (isotropic Gaussian) over the latent space. Hence, we further propose a mitigation of this issue by introducing constrained adaptive prior (CAP) for learning user- and item-dependent prior distributions. Empirical results on several real-world datasets show that the proposed model outperforms conventional VAE and other comparative collaborative filtering models in terms of item recommendation. Moreover, the proposed CAP further boosts the performance of BiVAE. An implementation of BiVAE is available on Cornac recommender library.

Keywords

collaborative filtering, dyadic data, variational autoencoder

Discipline

Databases and Information Systems | Data Science

Research Areas

Data Science and Engineering

Publication

WSDM '21: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Virtual, March 8-12

First Page

292

Last Page

300

ISBN

9781450382977

Identifier

10.1145/3437963.3441759

Publisher

ACM

City or Country

New York

Embargo Period

5-20-2021

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3437963.3441759

Share

COinS