dc.contributor.advisor | Szlichta, Jarek | |
dc.contributor.advisor | Salehi-Abari, Amirali | |
dc.contributor.author | Askari Firoozjayi, Bahare | |
dc.date.accessioned | 2021-02-26T15:17:29Z | |
dc.date.accessioned | 2022-03-29T17:26:06Z | |
dc.date.available | 2021-02-26T15:17:29Z | |
dc.date.available | 2022-03-29T17:26:06Z | |
dc.date.issued | 2020-12-01 | |
dc.identifier.uri | https://hdl.handle.net/10155/1246 | |
dc.description.abstract | Recently, Variational Autoencoders (VAEs) have shown remarkable performance in collaborative filtering (CF) with implicit feedback. These existing recommendation models learn user representations to reconstruct or predict user preferences. However, existing VAE-based recommendation models learn user and item representations separately. This thesis introduces joint variational autoencoders (JoVA). JoVA, as an ensemble of two VAEs, simultaneously and jointly learns both user-user and item-item correlations and collectively reconstructs and predicts user preferences. Moreover, a variant of JoVA, referred to as JoVA-Hinge, is introduced to improve recommendation quality. JoVA-Hinge incorporates pairwise ranking loss to VAE's losses. Extensive experiments on multiple real-world datasets show that our model can outperform state-of-the-art under a variety of commonly-used metrics. Our empirical experiments also confirm that JoVA-Hinge offers better results than existing methods for cold-start users with limited training data. | en |
dc.description.sponsorship | University of Ontario Institute of Technology | en |
dc.language.iso | en | en |
dc.subject | Recommender systems | en |
dc.subject | Deep learning | en |
dc.subject | Variational Autoencoder | en |
dc.subject | Hinge based loss function | en |
dc.title | JoVA-hinge: joint variational autoencoders for personalized recommendation with implicit feedback | en |
dc.type | Thesis | en |
dc.degree.level | Master of Science (MSc) | en |
dc.degree.discipline | Computer Science | en |