Representation Quantization for Collaborative Filtering Augmentation

2025-08-15

AI Summary

To address insufficient user-item associations caused by data sparsity in collaborative filtering (CF), this paper proposes DQRec, a two-stage recommendation model. Methodologically, it introduces the Decomposed Quantized Variational Autoencoder (DQ-VAE), the first to incorporate vector quantization into CF representation learning; it jointly models interaction sequences and item attributes to capture fine-grained behavioral patterns and subsequently generates semantic IDs for multi-dimensional user interest modeling, homophilous neighbor expansion, and semantic-level information propagation. Key contributions include: (1) integrating vector quantization with variational autoencoding to enhance CF representations, and (2) achieving dual enhancement of feature semantics and graph structure via pre-trained representation decomposition and semantic ID generation. Extensive experiments on multiple public benchmarks demonstrate significant improvements over state-of-the-art baselines, effectively alleviating data sparsity while boosting recommendation accuracy and information diffusion efficiency.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking user-user and item-item homogeneous linkages. However, existing methods are typically limited to connecting through overlapping interacted neighbors or through similar attributes and contents. These approaches are constrained by coarse-grained, sparse attributes and fail to effectively extract behavioral characteristics jointly from interaction sequences and attributes. To address these challenges, we propose a novel two-stage collaborative recommendation algorithm, DQRec: Decomposition-based Quantized Variational AutoEncoder (DQ-VAE) for Recommendation. DQRec augments features and homogeneous linkages by extracting the behavior characteristics jointly from interaction sequences and attributes, namely patterns, such as user multi-aspect interests. Inspired by vector quantization (VQ) technology, we propose a new VQ algorithm, DQ-VAE, which decomposes the pre-trained representation embeddings into distinct dimensions, and quantize them to generates semantic IDs. We utilize the generated semantic IDs as the extracted patterns mentioned above. By integrating these semantic ID patterns into the recommendation process through feature and linkage augmentation, the system enriches both latent and explicit user and item features, identifies pattern-similar neighbors, and thereby improves the efficiency of information diffusion. Experimental comparisons with baselines across multiple datasets demonstrate the superior performance of the proposed DQRec method.

Problem

• Addresses data sparsity in collaborative filtering recommendation systems
• Enhances linkage augmentation by jointly analyzing interactions and attributes
• Improves recommendation accuracy via decomposed quantized variational autoencoder

Innovation

• DQ-VAE decomposes and quantizes representation embeddings
• Generates semantic IDs for user-item behavior patterns
• Augments features and linkages using semantic IDs