Flow Matching based Sequential Recommender Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Feng, Zou, Lixin, Zhao, Xiangyu, Tang, Min, Dong, Liming, Luo, Dan, Luo, Xiangyang, Li, Chenliang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912387061252096
author Liu, Feng
Zou, Lixin
Zhao, Xiangyu
Tang, Min
Dong, Liming
Luo, Dan
Luo, Xiangyang
Li, Chenliang
author_facet Liu, Feng
Zou, Lixin
Zhao, Xiangyu
Tang, Min
Dong, Liming
Luo, Dan
Luo, Xiangyang
Li, Chenliang
contents Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and reverse processes of diffusion-based methods. Towards this end, this study introduces FMRec, a Flow Matching based model that employs a straight flow trajectory and a modified loss tailored for the recommendation task. Additionally, from the diffusion-model perspective, we integrate a reconstruction loss to improve robustness against noise perturbations, thereby retaining user preferences during the forward process. In the reverse process, we employ a deterministic reverse sampler, specifically an ODE-based updating function, to eliminate unnecessary randomness, thereby ensuring that the generated recommendations closely align with user needs. Extensive evaluations on four benchmark datasets reveal that FMRec achieves an average improvement of 6.53% over state-of-the-art methods. The replication code is available at https://github.com/FengLiu-1/FMRec.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16298
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flow Matching based Sequential Recommender Model
Liu, Feng
Zou, Lixin
Zhao, Xiangyu
Tang, Min
Dong, Liming
Luo, Dan
Luo, Xiangyang
Li, Chenliang
Information Retrieval
Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and reverse processes of diffusion-based methods. Towards this end, this study introduces FMRec, a Flow Matching based model that employs a straight flow trajectory and a modified loss tailored for the recommendation task. Additionally, from the diffusion-model perspective, we integrate a reconstruction loss to improve robustness against noise perturbations, thereby retaining user preferences during the forward process. In the reverse process, we employ a deterministic reverse sampler, specifically an ODE-based updating function, to eliminate unnecessary randomness, thereby ensuring that the generated recommendations closely align with user needs. Extensive evaluations on four benchmark datasets reveal that FMRec achieves an average improvement of 6.53% over state-of-the-art methods. The replication code is available at https://github.com/FengLiu-1/FMRec.
title Flow Matching based Sequential Recommender Model
topic Information Retrieval
url https://arxiv.org/abs/2505.16298