Year: 2025
Type: preprint
Abstract: Sequential recommendation aims to predict each user's next preferred item based on their historical interactions. Recently, diffusion-based approaches have demonstrated strong generative capability in modeling complex user preferences. However, they still face two inherent limitations: (i) Gaussian priors are misaligned with user-specific interests, and curved noise schedules lead to error accumulation and unstable training; (ii) the stochastic denoising process introduces additional randomness and substantial computational overhead. To address these issues, we propose FlowRec, a flow-matching-based framework that formulates preference evolution as continuous flows between personalized priors and target items. Specifically, FlowRec constructs an informative behavior-based prior distribution derived from users' historical interactions, offering a distributionally closer initialization to the target distribution. It then learns a vector field to guide straight preference flows toward target interests. Moreover, a single-step alignment objective with positive and negative samples further enhances semantic consistency between generated representations and ground-truth items. Finally, FlowRec adopts deterministic ODE-based generation, achieving efficient and stable inference. Extensive experiments on multiple benchmark datasets demonstrate that FlowRec consistently outperforms state-of-the-art baselines in both recommendation accuracy and inference efficiency.
Source: arXiv (Cornell University)
Authors: Li, Li, Cheng, Mingyue, Ye, Yuyang, Liu, Zhiding, Chen, Enhong
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G7967803912
OpenAlex ID: W7077974033
Cites:
Cited by:
Related to: