---
title: "PDFlow: Popularity-Debiased Flow Matching for Sequential Recommendation"
authors:
  - "Zican Yang"
  - "Zeyu Li"
  - "Cong He"
  - "Xiaotao Wu"
  - "Guanfeng Liu"
  - "Pengpeng Zhao"
doi: "10.24963/ijcai.2026/353"
url: "https://ijcai.org/proceedings/2026/353"
pdf: "https://ijcai.org/proceedings/2026/0353.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3178-3186"
track: "Main Track"
keywords:
  - "Data Mining: Recommender systems"
---

# PDFlow: Popularity-Debiased Flow Matching for Sequential Recommendation

Zican Yang, Zeyu Li, Cong He, Xiaotao Wu, Guanfeng Liu, Pengpeng Zhao

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3178-3186. DOI: [10.24963/ijcai.2026/353](https://doi.org/10.24963/ijcai.2026/353)

## Abstract

Generative models have emerged as a powerful paradigm in sequential recommendation due to their superior distribution modeling. However, long-tail data distributions inevitably induce popularity bias, as iterative generation trajectories gravitate toward dense clusters of popular items. Current debiasing methods struggle to enforce consistent step-wise constraints, rendering them ineffective for the multi-step process of generative recommendation. To address this challenge, we propose a method called Popularity-Debiased Flow Matching for sequential recommendation (PDFlow). Specifically, grounded in the flow matching framework, PDFlow integrates a residual popularity vector field beyond the main flow to model the popularity debiasing flow at each step. This enables real-time trajectory intervention to adjust the generative path, preventing the model from overemphasizing popular items. Subsequently, we incorporate cross-popularity alignment loss, using co-occurrence patterns within the same sequence to align features of both popular and tail items, thereby mitigating popularity-driven distribution separation. Jointly, trajectory correction prevents popularity overfitting while cross-popularity alignment ensures latent fairness, effectively mitigating popularity bias. Extensive experiments on four real-world datasets demonstrate the effectiveness of PDFlow in improving long-tail coverage and overall recommendation performance. All codes and  datasets are available at https://github.com/eqmll/PDFlow.