Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Luankang, Song, Kenan, Lee, Yi Quan, Guo, Wei, Wang, Hao, Li, Yawen, Guo, Huifeng, Liu, Yong, Lian, Defu, Chen, Enhong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915254870474752
author Zhang, Luankang
Song, Kenan
Lee, Yi Quan
Guo, Wei
Wang, Hao
Li, Yawen
Guo, Huifeng
Liu, Yong
Lian, Defu
Chen, Enhong
author_facet Zhang, Luankang
Song, Kenan
Lee, Yi Quan
Guo, Wei
Wang, Hao
Li, Yawen
Guo, Huifeng
Liu, Yong
Lian, Defu
Chen, Enhong
contents In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance. Recent advances in generative models, inspired by natural language processing, suggest the potential for unifying these stages to mitigate such loss. This paper presents the Unified Generative Recommendation Framework (UniGRF), a novel approach that integrates retrieval and ranking into a single generative model. By treating both stages as sequence generation tasks, UniGRF enables sufficient information sharing without additional computational costs, while remaining model-agnostic. To enhance inter-stage collaboration, UniGRF introduces a ranking-driven enhancer module that leverages the precision of the ranking stage to refine retrieval processes, creating an enhancement loop. Besides, a gradient-guided adaptive weighter is incorporated to dynamically balance the optimization of retrieval and ranking, ensuring synchronized performance improvements. Extensive experiments demonstrate that UniGRF significantly outperforms existing models on benchmark datasets, confirming its effectiveness in facilitating information transfer. Ablation studies and further experiments reveal that UniGRF not only promotes efficient collaboration between stages but also achieves synchronized optimization. UniGRF provides an effective, scalable, and compatible framework for generative recommendation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model
Zhang, Luankang
Song, Kenan
Lee, Yi Quan
Guo, Wei
Wang, Hao
Li, Yawen
Guo, Huifeng
Liu, Yong
Lian, Defu
Chen, Enhong
Information Retrieval
In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance. Recent advances in generative models, inspired by natural language processing, suggest the potential for unifying these stages to mitigate such loss. This paper presents the Unified Generative Recommendation Framework (UniGRF), a novel approach that integrates retrieval and ranking into a single generative model. By treating both stages as sequence generation tasks, UniGRF enables sufficient information sharing without additional computational costs, while remaining model-agnostic. To enhance inter-stage collaboration, UniGRF introduces a ranking-driven enhancer module that leverages the precision of the ranking stage to refine retrieval processes, creating an enhancement loop. Besides, a gradient-guided adaptive weighter is incorporated to dynamically balance the optimization of retrieval and ranking, ensuring synchronized performance improvements. Extensive experiments demonstrate that UniGRF significantly outperforms existing models on benchmark datasets, confirming its effectiveness in facilitating information transfer. Ablation studies and further experiments reveal that UniGRF not only promotes efficient collaboration between stages but also achieves synchronized optimization. UniGRF provides an effective, scalable, and compatible framework for generative recommendation systems.
title Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model
topic Information Retrieval
url https://arxiv.org/abs/2504.16454