# A Gated Hybrid Contrastive Collaborative Filtering Recommendation

arXiv: https://arxiv.org/abs/2604.27117 · HTML: https://mlsanity.com/paper/2604.27117/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [News Recommender System: A review of recent progress, challenges, and opportunities](https://mlsanity.com/paper/2009.04964/) (2020)
- [A Review-aware Graph Contrastive Learning Framework for Recommendation](https://mlsanity.com/paper/2204.12063/) (2022)
- [A Context-Aware User-Item Representation Learning for Item Recommendation](https://mlsanity.com/paper/1712.02342/) (2017)
- [Leveraging Review Properties for Effective Recommendation](https://mlsanity.com/paper/2102.03089/) (2021)
- [Do Reviews Matter for Recommendations in the Era of Large Language Models?](https://mlsanity.com/paper/2512.12978/) (2025)

## Abstract (arXiv)

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.