Unleash the Potential of Long Semantic IDs for Generative Recommendation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xia, Ming, Zhou, Zhiqin, Ma, Guoxin, Huang, Dongmin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918338086567936
author Xia, Ming
Zhou, Zhiqin
Ma, Guoxin
Huang, Dongmin
author_facet Xia, Ming
Zhou, Zhiqin
Ma, Guoxin
Huang, Dongmin
contents Semantic ID-based generative recommendation represents items as sequences of discrete tokens, but it inherently faces a trade-off between representational expressiveness and computational efficiency. Residual Quantization (RQ)-based approaches restrict semantic IDs to be short to enable tractable sequential modeling, while Optimized Product Quantization (OPQ)-based methods compress long semantic IDs through naive rigid aggregation, inevitably discarding fine-grained semantic information. To resolve this dilemma, we propose ACERec, a novel framework that decouples the granularity gap between fine-grained tokenization and efficient sequential modeling. It employs an Attentive Token Merger to distill long expressive semantic tokens into compact latents and introduces a dedicated Intent Token serving as a dynamic prediction anchor. To capture cohesive user intents, we guide the learning process via a dual-granularity objective, harmonizing fine-grained token prediction with global item-level semantic alignment. Extensive experiments on six real-world benchmarks demonstrate that ACERec consistently outperforms state-of-the-art baselines, achieving an average improvement of 14.40\% in NDCG@10, effectively reconciling semantic expressiveness and computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2602_13573
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unleash the Potential of Long Semantic IDs for Generative Recommendation
Xia, Ming
Zhou, Zhiqin
Ma, Guoxin
Huang, Dongmin
Information Retrieval
Semantic ID-based generative recommendation represents items as sequences of discrete tokens, but it inherently faces a trade-off between representational expressiveness and computational efficiency. Residual Quantization (RQ)-based approaches restrict semantic IDs to be short to enable tractable sequential modeling, while Optimized Product Quantization (OPQ)-based methods compress long semantic IDs through naive rigid aggregation, inevitably discarding fine-grained semantic information. To resolve this dilemma, we propose ACERec, a novel framework that decouples the granularity gap between fine-grained tokenization and efficient sequential modeling. It employs an Attentive Token Merger to distill long expressive semantic tokens into compact latents and introduces a dedicated Intent Token serving as a dynamic prediction anchor. To capture cohesive user intents, we guide the learning process via a dual-granularity objective, harmonizing fine-grained token prediction with global item-level semantic alignment. Extensive experiments on six real-world benchmarks demonstrate that ACERec consistently outperforms state-of-the-art baselines, achieving an average improvement of 14.40\% in NDCG@10, effectively reconciling semantic expressiveness and computational efficiency.
title Unleash the Potential of Long Semantic IDs for Generative Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2602.13573