Temporal collaborative filtering (TCF) methods aim at modelling non-static aspects behind recommender systems, such as the dynamics in users{\textquoteright} 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 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 makes it more complicated to obtain 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 nontemporal CF models.
Rodrigo Bonet, E, Nguyen, MD & Deligiannis, N 2020, Temporal Collaborative Filtering with Graph Convolutional Neural Networks. in 25th International Conference on Pattern Recognition (ICPR)., 9413200, Proceedings - International Conference on Pattern Recognition, IEEE, pp. 4736-4742, 25th IEEE International Conference on Pattern Recognition, Milan, Italy, 10/01/21. https://doi.org/10.1109/ICPR48806.2021.9413200, https://doi.org/10.1109/ICPR48806.2021.9413200
Rodrigo Bonet, E., Nguyen, M. D., & Deligiannis, N. (2020). Temporal Collaborative Filtering with Graph Convolutional Neural Networks. In 25th International Conference on Pattern Recognition (ICPR) (pp. 4736-4742). Article 9413200 (Proceedings - International Conference on Pattern Recognition). IEEE. https://doi.org/10.1109/ICPR48806.2021.9413200, https://doi.org/10.1109/ICPR48806.2021.9413200
@inproceedings{718fd4744d8c4de5afed1705543f69c8,
title = "Temporal Collaborative Filtering with Graph Convolutional Neural Networks",
abstract = "Temporal collaborative filtering (TCF) methods aim at modelling non-static aspects behind recommender systems, such as the dynamics in users{\textquoteright} 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 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 makes it more complicated to obtain 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 nontemporal CF models.",
author = "\{Rodrigo Bonet\}, Esther and Nguyen, \{Minh Duc\} and Nikolaos Deligiannis",
year = "2020",
doi = "10.1109/ICPR48806.2021.9413200",
language = "English",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "IEEE",
pages = "4736--4742",
booktitle = "25th International Conference on Pattern Recognition (ICPR)",
note = "25th IEEE International Conference on Pattern Recognition ; Conference date: 10-01-2021 Through 15-01-2021",
url = "http://www.icpr2020.it/",
}