A Gated Hybrid Contrastive Collaborative Filtering Recommendation

2026-04-29

AI Summary

This work addresses the limited effectiveness of existing review-integrated recommender systems in enhancing Top-N ranking performance, as they predominantly focus on rating prediction. To overcome this limitation, the authors propose a gated hybrid contrastive collaborative filtering framework that progressively injects review semantics through an autoencoder, leveraging both topic modeling and text embeddings to extract rich semantic features. An adaptive gating mechanism dynamically fuses collaborative signals with semantic representations, while contrastive learning aligns these two types of embeddings. Furthermore, Bayesian Personalized Ranking is employed as the optimization objective to explicitly enhance ranking quality. Extensive experiments on Amazon Movies & TV, IMDb, and Rotten Tomatoes datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in terms of Hit Rate@10 and NDCG@10, confirming the efficacy of controllable semantic fusion and contrastive alignment for improving recommendation ranking performance.

Abstract

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.

Problem

• recommender systems
• top-N recommendation
• ranking quality
• review-aware models
• collaborative filtering

Innovation

• Gated Fusion
• Contrastive Learning
• Collaborative Filtering
• Review-aware Recommendation
• Ranking Optimization