Temporal Collaborative Filtering with Graph Convolutional Neural Networks

TL;DR

This paper introduces a novel temporal collaborative filtering approach that combines graph neural networks and recurrent neural networks to better model dynamic user preferences and social trends, demonstrating improved recommendation accuracy.

Contribution

It proposes integrating GNNs with RNNs for temporal CF, addressing data sparsity by training GNNs at each time step, and shows superior performance over existing models.

Findings

Enhanced recommendation accuracy on real-world datasets

GNN-RNN hybrid outperforms traditional MF and RNN-based models

Effective handling of data sparsity in temporal settings

Abstract

Temporal collaborative filtering (TCF) methods aim at modelling non-static aspects behind recommender systems, such as the dynamics in users' preferences and social trends around items. State-of-the-art TCF methods employ recurrent neural networks (RNNs) to model such aspects. These methods deploy matrix-factorization-based (MF-based) approaches to learn the user and item representations. Recently, graph-neural-network-based (GNN-based) approaches have shown improved performance in providing accurate recommendations over traditional MF-based approaches in non-temporal CF settings. Motivated by this, we propose a novel TCF method that leverages GNNs to learn user and item representations, and RNNs to model their temporal dynamics. A challenge with this method lies in the increased data sparsity, which negatively impacts obtaining meaningful quality representations with GNNs. To overcome this challenge, we train a GNN model at each time step using a set of observed interactions accumulated time-wise. Comprehensive experiments on real-world data show the improved performance obtained by our method over several state-of-the-art temporal and non-temporal CF models.