cs.IROct 31, 2026

SIDRec: End-to-End Semantic ID Representation and Modeling for Recommendation

Authors: Zhuohang Jiang, Yongsen Pan, Pangjing Wu, Zihuai Zhao, Zheng Hu, Yuxin Chen

Organizations: The Hong Kong Polytechnic University, Hong Kong SAR, China · University of Electronic Science and Technology of China, Chengdu, SiChuan, China · Southwest Jiaotong University, Chengdu, SiChuan, China · Kuaishou Technology, Beijing, China

Abstract

Semantic IDs (SIDs) have emerged as a promising approach for discriminative recommendation by encoding continuous item rep- resentations into compact discrete identifiers. However, existing SID-based methods face two fundamental limitations: semantic mis- match between content semantics and collaborative preferences, and objective mismatch between SID construction and downstream recommendation optimization. To address these challenges, we propose SIDRec, an end-to-end recommendation-aware SID learn- ing framework that jointly models content and collaborative in- formation while aligning SID construction with recommendation objectives. Specifically, SIDRec introduces a self-updating fusion mechanism that explicitly integrates pretrained content represen- tations with collaborative embeddings initialized from a trained recommendation model, enabling preference-aware semantic mod- eling. Furthermore, SIDRec employs an MMoE-inspired joint opti- mization mechanism with shared experts and task-specific gates, allowing recommendation supervision to directly guide differen- tiable quantization and produce task-adaptive discrete representa- tions. Extensive experiments on three public benchmark datasets demonstrate that SIDRec consistently outperforms all competing methods across both AUC and GAUC, achieving up to 5.15% relative improvements over the strongest baselines. Further ablation stud- ies validate the effectiveness and complementarity of collaborative semantic modeling and end-to-end SID optimization.

Figures & tables

Explore similar work

CardsList
  1. The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation

    Dec 11, 2025Ziwei Liu, Yejing Wang, Wanyu Wang +6Semantic ID RecommendationSequential Recommendation

  2. Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale

    Feb 28, 2026Zheng Hu, Yuxin Chen, Yongsen Pan +13Semantic ID RecommendationMultimodal Recommendation

  3. Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)

    Oct 1, 2026Aleksei Medvedev, Alejandro Ariza-Casabona, Steven Derby +3Semantic ID RecommendationGraph Clustering