{"id":{"repo_id":"uoit","oai_identifier":"oai:ontariotechu.scholaris.ca:10155/1246"},"canonical_url":"https://search.dev.ndltd.org/etd/uoit/oai:ontariotechu.scholaris.ca:10155/1246","repository":{"repo_id":"uoit","name":"Ontario Institute of Technology","base_url":"https://ontariotechu.scholaris.ca/server/oai/request"},"display":{"title":"JoVA-hinge: joint variational autoencoders for personalized recommendation with implicit feedback","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Askari Firoozjayi, Bahare"],"institution":"University of Ontario Institute of Technology","degree_name":"Master of Science (MSc)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Szlichta, Jarek","Salehi-Abari, Amirali"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-12-01","date_published":"2020-12-01","updated_at":"2026-07-24T05:35:24Z","subjects":["Recommender systems","Deep learning","Variational Autoencoder","Hinge based loss function"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10155/1246","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Szlichta, Jarek","Salehi-Abari, Amirali"]},{"key":"dc:creator","label":"Author","values":["Askari Firoozjayi, Bahare"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-02-26T15:17:29Z","2022-03-29T17:26:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-02-26T15:17:29Z","2022-03-29T17:26:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-12-01"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MSc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Ontario Institute of Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Recommender systems","Deep learning","Variational Autoencoder","Hinge based loss function"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10155/1246"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:title","label":"Title","values":["JoVA-hinge: joint variational autoencoders for personalized recommendation with implicit feedback"]}]}],"canonical_facts":{"dc:contributor.advisor":["Szlichta, Jarek","Salehi-Abari, Amirali"],"dc:creator":["Askari Firoozjayi, Bahare"],"dc:date.accessioned":["2021-02-26T15:17:29Z","2022-03-29T17:26:06Z"],"dc:date.available":["2021-02-26T15:17:29Z","2022-03-29T17:26:06Z"],"dc:date.issued":["2020-12-01"],"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."],"dc:identifier.uri":["https://hdl.handle.net/10155/1246"],"dc:language.iso":["en"],"dc:subject":["Recommender systems","Deep learning","Variational Autoencoder","Hinge based loss function"],"dc:title":["JoVA-hinge: joint variational autoencoders for personalized recommendation with implicit feedback"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science (MSc)"],"thesis:institution_name":["University of Ontario Institute of Technology"]},"updated_at":"2026-07-24T05:35:24Z"}