Temporal Collaborative Filtering with Graph Convolutional Neural Networks
This work addresses the challenge of data sparsity in temporal recommender systems, offering a novel hybrid approach that could enhance recommendation accuracy for users in dynamic environments.
The paper tackled the problem of modeling dynamic user preferences and social trends in recommender systems by proposing a temporal collaborative filtering method that combines graph neural networks (GNNs) for learning user and item representations with recurrent neural networks (RNNs) for temporal dynamics, showing improved performance over state-of-the-art models in experiments on real-world data.
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.