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

TL;DR

This paper introduces PIMI, a novel sequential recommendation method that models user interests by incorporating periodicity and interactivity in item sequences, leading to improved recommendation accuracy.

Contribution

The paper proposes a multi-interest framework that effectively captures periodicity and interactivity, advancing sequential recommendation models beyond existing approaches.

Findings

PIMI outperforms state-of-the-art methods on Amazon and Taobao datasets.

The periodicity-aware module effectively utilizes time interval information.

The interactivity graph captures both global and local item features.

Abstract

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.