Factorial User Modeling with Hierarchical Graph Neural Network for Enhanced Sequential Recommendation

TL;DR

This paper introduces a hierarchical graph neural network for sequential recommendation that models user preferences across multiple factors and incorporates timespan information, leading to improved recommendation accuracy.

Contribution

It proposes a novel hierarchical GNN approach with timespan-aware graphs and factor clustering to better capture diverse user preferences in sequential recommendation.

Findings

Outperforms state-of-the-art SR models on two datasets.

Effectively models diverse user preferences with hierarchical clustering.

Utilizes timespan information to enhance recommendation accuracy.

Abstract

Most sequential recommendation (SR) systems employing graph neural networks (GNNs) only model a user's interaction sequence as a flat graph without hierarchy, overlooking diverse factors in the user's preference. Moreover, the timespan between interacted items is not sufficiently utilized by previous models, restricting SR performance gains. To address these problems, we propose a novel SR system employing a hierarchical graph neural network (HGNN) to model factorial user preferences. Specifically, a timespan-aware sequence graph (TSG) for the target user is first constructed with the timespan among interacted items. Next, all original nodes in TSG are softly clustered into factor nodes, each of which represents a certain factor of the user's preference. At last, all factor nodes' representations are used together to predict SR results. Our extensive experiments upon two datasets justify that our HGNN-based factorial user modeling obtains better SR performance than the state-of-the-art SR models.