Saved in:
Bibliographic Details
Main Authors: Li, Kaiyuan, Xiang, Rui, Bai, Yong, Tang, Yongxiang, Cheng, Yanhua, Liu, Xialong, Jiang, Peng, Gai, Kun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.06636
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908308813643776
author Li, Kaiyuan
Xiang, Rui
Bai, Yong
Tang, Yongxiang
Cheng, Yanhua
Liu, Xialong
Jiang, Peng
Gai, Kun
author_facet Li, Kaiyuan
Xiang, Rui
Bai, Yong
Tang, Yongxiang
Cheng, Yanhua
Liu, Xialong
Jiang, Peng
Gai, Kun
contents Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit large language models to encode modalities into discrete semantic IDs for autoregressive prediction, we identify two critical limitations: (1) Existing approaches adopt fragmented quantization, where modalities are independently mapped to semantic spaces misaligned with behavioral objectives, and (2) Over-reliance on semantic IDs disrupts inter-modal semantic coherence, thereby weakening the expressive power of multi-modal representations for modeling diverse user preferences. To address these challenges, we propose a Behavior-Bind multi-modal Quantization for Sequential Recommendation (BBQRec for short) featuring dual-aligned quantization and semantics-aware sequence modeling. First, our behavior-semantic alignment module disentangles modality-agnostic behavioral patterns from noisy modality-specific features through contrastive codebook learning, ensuring semantic IDs are inherently tied to recommendation tasks. Second, we design a discretized similarity reweighting mechanism that dynamically adjusts self-attention scores using quantized semantic relationships, preserving multi-modal synergies while avoiding invasive modifications to the sequence modeling architecture. Extensive evaluations across four real-world benchmarks demonstrate BBQRec's superiority over the state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06636
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation
Li, Kaiyuan
Xiang, Rui
Bai, Yong
Tang, Yongxiang
Cheng, Yanhua
Liu, Xialong
Jiang, Peng
Gai, Kun
Information Retrieval
Multi-modal sequential recommendation systems leverage auxiliary signals (e.g., text, images) to alleviate data sparsity in user-item interactions. While recent methods exploit large language models to encode modalities into discrete semantic IDs for autoregressive prediction, we identify two critical limitations: (1) Existing approaches adopt fragmented quantization, where modalities are independently mapped to semantic spaces misaligned with behavioral objectives, and (2) Over-reliance on semantic IDs disrupts inter-modal semantic coherence, thereby weakening the expressive power of multi-modal representations for modeling diverse user preferences. To address these challenges, we propose a Behavior-Bind multi-modal Quantization for Sequential Recommendation (BBQRec for short) featuring dual-aligned quantization and semantics-aware sequence modeling. First, our behavior-semantic alignment module disentangles modality-agnostic behavioral patterns from noisy modality-specific features through contrastive codebook learning, ensuring semantic IDs are inherently tied to recommendation tasks. Second, we design a discretized similarity reweighting mechanism that dynamically adjusts self-attention scores using quantized semantic relationships, preserving multi-modal synergies while avoiding invasive modifications to the sequence modeling architecture. Extensive evaluations across four real-world benchmarks demonstrate BBQRec's superiority over the state-of-the-art baselines.
title BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2504.06636