A Contrastive Framework with User, Item and Review Alignment for Recommendation

2025-01-21

AI Summary

To address user-item interaction sparsity and underutilization of review information in recommender systems, this paper proposes ReCAFR, a review-centric contrastive alignment framework. ReCAFR is the first method to deeply integrate reviews into the core user-item representation learning pipeline—constructing a collaborative latent space for joint alignment of users, items, and reviews, rather than relying on shallow feature concatenation. It employs self-supervised contrastive learning, multi-granularity text augmentation, and cross-modal alignment to mitigate review scarcity and modality fragmentation, while leveraging graph neural networks to model implicit interactions. Extensive experiments on multiple benchmark datasets demonstrate that ReCAFR significantly outperforms state-of-the-art methods: notably, it achieves a 12.7% improvement in Recall@20 under low-density scenarios, validating its robustness and generalization capability.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Learning effective latent representations for users and items is the cornerstone of recommender systems. Traditional approaches rely on user-item interaction data to map users and items into a shared latent space, but the sparsity of interactions often poses challenges. While leveraging user reviews could mitigate this sparsity, existing review-aware recommendation models often exhibit two key limitations. First, they typically rely on reviews as additional features, but reviews are not universal, with many users and items lacking them. Second, such approaches do not integrate reviews into the user-item space, leading to potential divergence or inconsistency among user, item, and review representations. To overcome these limitations, our work introduces a Review-centric Contrastive Alignment Framework for Recommendation (ReCAFR), which incorporates reviews into the core learning process, ensuring alignment among user, item, and review representations within a unified space. Specifically, we leverage two self-supervised contrastive strategies that not only exploit review-based augmentation to alleviate sparsity, but also align the tripartite representations to enhance robustness. Empirical studies on public benchmark datasets demonstrate the effectiveness and robustness of ReCAFR.

Problem

• Sparse User-Item Data
• Information Consistency
• Recommendation Accuracy and Stability

Innovation

• ReCAFR
• Evaluation Integration
• Self-learning Methods