Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation

TL;DR

This paper introduces DRL-SRe, a novel model that captures dynamic user and item representations from time-sliced interaction graphs using graph neural networks and temporal prediction, significantly improving sequential recommendation accuracy.

Contribution

The paper proposes a dual dynamic representation learning framework utilizing time-sliced graphs and temporal point processes for enhanced sequential recommendation.

Findings

DRL-SRe outperforms state-of-the-art models on three real-world datasets.

The use of time-sliced graphs effectively captures temporal dynamics.

Auxiliary temporal prediction improves recommendation performance.

Abstract

Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items. While modeling temporal dynamics is crucial for sequential recommendation, most of the existing studies concentrate solely on the user side while overlooking the sequential patterns existing in the counterpart, i.e., the item side. Although a few studies investigate the dynamics involved in the dual sides, the complex user-item interactions are not fully exploited from a global perspective to derive dynamic user and item representations. In this paper, we devise a novel Dynamic Representation Learning model for Sequential Recommendation (DRL-SRe). To better model the user-item interactions for characterizing the dynamics from both sides, the proposed model builds a global user-item interaction graph for each time slice and exploits time-sliced graph neural networks to learn user and item representations. Moreover, to enable the model to capture fine-grained temporal information, we propose an auxiliary temporal prediction task over consecutive time slices based on temporal point process. Comprehensive experiments on three public real-world datasets demonstrate DRL-SRe outperforms the state-of-the-art sequential recommendation models with a large margin.