A Gated Hybrid Contrastive Collaborative Filtering Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: da Silva, Eduardo Ferreira, Oliveira, Mayki dos Santos, Pires, Joel Machado, Boaventura, Denis Dantas, Peixoto, Maycon Maciel, Prazeres, Cassio Serafim, Figueiredo, Gustavo Bittencourt, Capretz, Miriam, Durão, Frederico Araujo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911633511546880
author da Silva, Eduardo Ferreira
Oliveira, Mayki dos Santos
Pires, Joel Machado
Boaventura, Denis Dantas
Peixoto, Maycon Maciel
Prazeres, Cassio Serafim
Figueiredo, Gustavo Bittencourt
Capretz, Miriam
Durão, Frederico Araujo
author_facet da Silva, Eduardo Ferreira
Oliveira, Mayki dos Santos
Pires, Joel Machado
Boaventura, Denis Dantas
Peixoto, Maycon Maciel
Prazeres, Cassio Serafim
Figueiredo, Gustavo Bittencourt
Capretz, Miriam
Durão, Frederico Araujo
contents Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their effectiveness in top-N recommendation scenarios, where discriminative ranking is essential. To address this gap, we propose a Gated Hybrid Collaborative Filtering framework that integrates review-derived representations into an autoencoder-based collaborative model. The architecture injects semantic signals layer-wise through an adaptive gating mechanism that dynamically balances collaborative embeddings and topic-based features during encoding. To further refine the latent space, we introduce a contrastive learning module that aligns semantic and collaborative signals. We evaluate the framework across five distinct configurations: Pure collaborative; Topic and Gated; Text and Gated; and the addition of contrastive objectives (Contrastive and Topic, and Contrastive and Text). To explicitly optimize ranking behavior, the model is trained with a pairwise Bayesian personalized ranking objective, which promotes separation between relevant and non-relevant items in the latent space. Experiments on Amazon Movies & TV, IMDb, and Rotten Tomatoes demonstrate consistent improvements in hit rate @10 and normalized discounted cumulative gain @10 over state-of-the-art review-aware baselines. Results highlight the importance of controlled semantic fusion for ranking-driven recommendation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27117
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Gated Hybrid Contrastive Collaborative Filtering Recommendation
da Silva, Eduardo Ferreira
Oliveira, Mayki dos Santos
Pires, Joel Machado
Boaventura, Denis Dantas
Peixoto, Maycon Maciel
Prazeres, Cassio Serafim
Figueiredo, Gustavo Bittencourt
Capretz, Miriam
Durão, Frederico Araujo
Information Retrieval
Artificial Intelligence
Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their effectiveness in top-N recommendation scenarios, where discriminative ranking is essential. To address this gap, we propose a Gated Hybrid Collaborative Filtering framework that integrates review-derived representations into an autoencoder-based collaborative model. The architecture injects semantic signals layer-wise through an adaptive gating mechanism that dynamically balances collaborative embeddings and topic-based features during encoding. To further refine the latent space, we introduce a contrastive learning module that aligns semantic and collaborative signals. We evaluate the framework across five distinct configurations: Pure collaborative; Topic and Gated; Text and Gated; and the addition of contrastive objectives (Contrastive and Topic, and Contrastive and Text). To explicitly optimize ranking behavior, the model is trained with a pairwise Bayesian personalized ranking objective, which promotes separation between relevant and non-relevant items in the latent space. Experiments on Amazon Movies & TV, IMDb, and Rotten Tomatoes demonstrate consistent improvements in hit rate @10 and normalized discounted cumulative gain @10 over state-of-the-art review-aware baselines. Results highlight the importance of controlled semantic fusion for ranking-driven recommendation.
title A Gated Hybrid Contrastive Collaborative Filtering Recommendation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2604.27117