FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shi, Ke, Zhang, Yao, Guo, Feng, Zhang, Jinyuan, Zhang, JunShuo, Gao, Shen, Shang, Shuo
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911569083891712
author Shi, Ke
Zhang, Yao
Guo, Feng
Zhang, Jinyuan
Zhang, JunShuo
Gao, Shen
Shang, Shuo
author_facet Shi, Ke
Zhang, Yao
Guo, Feng
Zhang, Jinyuan
Zhang, JunShuo
Gao, Shen
Shang, Shuo
contents Generative recommendation has emerged as a transformative paradigm for capturing the dynamic evolution of user intents in sequential recommendation. While flow-based methods improve the efficiency of diffusion models, they remain hindered by the ``Noise-to-Data'' paradigm, which introduces two critical inefficiencies: prior mismatch, where generation starts from uninformative noise, forcing a lengthy recovery trajectory; and linear redundancy, where iterative solvers waste computation on modeling deterministic preference transitions. To address these limitations, we propose a Flow-based Average Velocity Establishment (Fave) framework for one-step generation recommendation that learns a direct trajectory from an informative prior to the target distribution. Fave is structured via a progressive two-stage training strategy. In Stage 1, we establish a stable preference space through dual-end semantic alignment, applying constraints at both the source (user history) and target (next item) to prevent representation collapse. In Stage 2, we directly resolve the efficiency bottlenecks by introducing a semantic anchor prior, which initializes the flow with a masked embedding from the user's interaction history, providing an informative starting point. Then we learn a global average velocity, consolidating the multi-step trajectory into a single displacement vector, and enforce trajectory straightness via a JVP-based consistency constraint to ensure one-step generation. Extensive experiments on three benchmarks demonstrate that Fave not only achieves state-of-the-art recommendation performance but also delivers an order-of-magnitude improvement in inference efficiency, making it practical for latency-sensitive scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04427
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
Shi, Ke
Zhang, Yao
Guo, Feng
Zhang, Jinyuan
Zhang, JunShuo
Gao, Shen
Shang, Shuo
Information Retrieval
Computation and Language
Generative recommendation has emerged as a transformative paradigm for capturing the dynamic evolution of user intents in sequential recommendation. While flow-based methods improve the efficiency of diffusion models, they remain hindered by the ``Noise-to-Data'' paradigm, which introduces two critical inefficiencies: prior mismatch, where generation starts from uninformative noise, forcing a lengthy recovery trajectory; and linear redundancy, where iterative solvers waste computation on modeling deterministic preference transitions. To address these limitations, we propose a Flow-based Average Velocity Establishment (Fave) framework for one-step generation recommendation that learns a direct trajectory from an informative prior to the target distribution. Fave is structured via a progressive two-stage training strategy. In Stage 1, we establish a stable preference space through dual-end semantic alignment, applying constraints at both the source (user history) and target (next item) to prevent representation collapse. In Stage 2, we directly resolve the efficiency bottlenecks by introducing a semantic anchor prior, which initializes the flow with a masked embedding from the user's interaction history, providing an informative starting point. Then we learn a global average velocity, consolidating the multi-step trajectory into a single displacement vector, and enforce trajectory straightness via a JVP-based consistency constraint to ensure one-step generation. Extensive experiments on three benchmarks demonstrate that Fave not only achieves state-of-the-art recommendation performance but also delivers an order-of-magnitude improvement in inference efficiency, making it practical for latency-sensitive scenarios.
title FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2604.04427