---
title: "SIDRec: End-to-End Semantic ID Representation and Modeling for Recommendation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01136v1"
permalink: "https://feed.astralor.com/items/itm_d4ce9141c5258bc38863e5cc"
published: "2026-10-31T17:27:29.000Z"
score: 57
channel: "tech"
tags: ["多模态","SIDRec","End-to-End Semantic","Representation","Modeling","Recommendation Semantic IDs","SIDs","However"]
---

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

## 速览

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 fu…

## 关键点

- 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 recommend…
- 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…

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d4ce9141c5258bc38863e5cc