Bilateral variational autoencoder for collaborative filtering
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 it...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/5952 https://ink.library.smu.edu.sg/context/sis_research/article/6955/viewcontent/wsdm21b.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-6955 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-69552021-05-21T01:28:07Z Bilateral variational autoencoder for collaborative filtering TRUONG, Quoc Tuan SALAH, Aghiles LAUW, Hady W. 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. 2021-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5952 info:doi/10.1145/3437963.3441759 https://ink.library.smu.edu.sg/context/sis_research/article/6955/viewcontent/wsdm21b.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University collaborative filtering dyadic data variational autoencoder Databases and Information Systems Data Science |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
collaborative filtering dyadic data variational autoencoder Databases and Information Systems Data Science |
spellingShingle |
collaborative filtering dyadic data variational autoencoder Databases and Information Systems Data Science TRUONG, Quoc Tuan SALAH, Aghiles LAUW, Hady W. Bilateral variational autoencoder for collaborative filtering |
description |
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. |
format |
text |
author |
TRUONG, Quoc Tuan SALAH, Aghiles LAUW, Hady W. |
author_facet |
TRUONG, Quoc Tuan SALAH, Aghiles LAUW, Hady W. |
author_sort |
TRUONG, Quoc Tuan |
title |
Bilateral variational autoencoder for collaborative filtering |
title_short |
Bilateral variational autoencoder for collaborative filtering |
title_full |
Bilateral variational autoencoder for collaborative filtering |
title_fullStr |
Bilateral variational autoencoder for collaborative filtering |
title_full_unstemmed |
Bilateral variational autoencoder for collaborative filtering |
title_sort |
bilateral variational autoencoder for collaborative filtering |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/5952 https://ink.library.smu.edu.sg/context/sis_research/article/6955/viewcontent/wsdm21b.pdf |
_version_ |
1770575702793388032 |