TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations

TL;DR

This paper introduces TEA, a novel sequential recommendation framework that models user behaviors and their influence over time using dynamic heterogeneous graphs, improving recommendation accuracy.

Contribution

The paper proposes a new framework that integrates temporal user-item graphs and user influence into sequential recommendation, using conditional random fields and pseudo-likelihood for scalable estimation.

Findings

Effective on three real-world datasets

Outperforms existing sequential recommendation methods

Provides insights into user influence dynamics

Abstract

Sequential recommendation aims to choose the most suitable items for a user at a specific timestamp given historical behaviors. Existing methods usually model the user behavior sequence based on the transition-based methods like Markov Chain. However, these methods also implicitly assume that the users are independent of each other without considering the influence between users. In fact, this influence plays an important role in sequence recommendation since the behavior of a user is easily affected by others. Therefore, it is desirable to aggregate both user behaviors and the influence between users, which are evolved temporally and involved in the heterogeneous graph of users and items. In this paper, we incorporate dynamic user-item heterogeneous graphs to propose a novel sequential recommendation framework. As a result, the historical behaviors as well as the influence between users can be taken into consideration. To achieve this, we firstly formalize sequential recommendation as a problem to estimate conditional probability given temporal dynamic heterogeneous graphs and user behavior sequences. After that, we exploit the conditional random field to aggregate the heterogeneous graphs and user behaviors for probability estimation, and employ the pseudo-likelihood approach to derive a tractable objective function. Finally, we provide scalable and flexible implementations of the proposed framework. Experimental results on three real-world datasets not only demonstrate the effectiveness of our proposed method but also provide some insightful discoveries on sequential recommendation.