# Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation

arXiv: https://arxiv.org/abs/2106.04415 · HTML: https://mlsanity.com/paper/2106.04415/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2021.

## Built on by (most cited first, 8 of 8)

- [Group-Aware Interest Disentangled Dual-Training for Personalized Recommendation](https://mlsanity.com/paper/2311.09577/) (2023)
- [Prompt Tuning for Item Cold-start Recommendation](https://mlsanity.com/paper/2412.18082/) (2024)
- [GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation](https://mlsanity.com/paper/2112.08717/) (2021)
- [Multi-Tower Multi-Interest Recommendation with User Representation Repel](https://mlsanity.com/paper/2403.05122/) (2024)
- [CoActionGraphRec: Sequential Multi-Interest Recommendations Using Co-Action Graphs](https://mlsanity.com/paper/2410.11464/) (2024)
- [GemiRec: Interest Quantization and Generation for Multi-Interest Recommendation](https://mlsanity.com/paper/2510.14626/) (2025)
- [TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation](https://mlsanity.com/paper/2604.09439/) (2026)
- [Denoising Implicit Feedback for Cold-start Recommendation](https://mlsanity.com/paper/2606.19658/) (2026)

## Abstract (arXiv)

Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in the literature. Most prior works usually obtain an overall representation based on the user's behavior sequence, which can not sufficiently reflect the multiple interests of the user. To this end, we propose a novel method called PIMI to mitigate this issue. PIMI can model the user's multi-interest representation effectively by considering both the periodicity and interactivity in the item sequence. Specifically, we design a periodicity-aware module to utilize the time interval information between user's behaviors. Meanwhile, an ingenious graph is proposed to enhance the interactivity between items in user's behavior sequence, which can capture both global and local item features. Finally, a multi-interest extraction module is applied to describe user's multiple interests based on the obtained item representation. Extensive experiments on two real-world datasets Amazon and Taobao show that PIMI outperforms state-of-the-art methods consistently.