Multi-Aggregator Time-Warping Heterogeneous Graph Neural Network for Personalized Micro-Video Recommendation

TL;DR

This paper introduces MTHGNN, a novel graph neural network model that captures the dynamic, timely preferences of users for personalized micro-video recommendation, outperforming existing methods.

Contribution

The paper proposes a multi-aggregator time-warping GNN that models micro-video characteristics and user preference dynamics for improved personalized recommendations.

Findings

MTHGNN outperforms state-of-the-art models in recommendation accuracy.

The model effectively captures temporal and dynamic user preferences.

Experimental results validate the superiority of the proposed approach.

Abstract

Micro-video recommendation is attracting global attention and becoming a popular daily service for people of all ages. Recently, Graph Neural Networks-based micro-video recommendation has displayed performance improvement for many kinds of recommendation tasks. However, the existing works fail to fully consider the characteristics of micro-videos, such as the high timeliness of news nature micro-video recommendation and sequential interactions of frequently changed interests. In this paper, a novel Multi-aggregator Time-warping Heterogeneous Graph Neural Network (MTHGNN) is proposed for personalized news nature micro-video recommendation based on sequential sessions, where characteristics of micro-videos are comprehensively studied, users' preference is mined via multi-aggregator, the temporal and dynamic changes of users' preference are captured, and timeliness is considered. Through the comparison with the state-of-the-arts, the experimental results validate the superiority of our MTHGNN model.