Pytorch geometric temporal: Spatiotemporal signal processing with neural machine learning models
Published in CIKM 2021, 2021
Recommended citation: Benedek Rozemberczki, Paul Scherer, Yixuan He, George Panagopoulos, Alexander Riedel, Maria Astefanoaei, Oliver Kiss, Ferenc Beres, Guzmán López, Nicolas Collignon and Rik Sarkar. PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models, Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp 4564–4573, 2021 https://dl.acm.org/doi/abs/10.1145/3459637.3482014
We present PyTorch Geometric Temporal, a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easy-to-use framework. PyTorch Geometric Temporal was created with foundations on existing libraries in the PyTorch eco-system, streamlined neural network layer definitions, temporal snapshot generators for batching, and integrated benchmark datasets. These features are illustrated with a tutorial-like case study. Experiments demonstrate the predictive performance of the models implemented in the library on real-world problems such as epidemiological forecasting, ride-hail demand prediction, and web traffic management. Our sensitivity analysis of runtime shows that the framework can potentially operate on web-scale datasets with rich temporal features and spatial structure.
Download the published version here
Citing the paper:
>@inproceedings{10.1145/3459637.3482014,
author = {Rozemberczki, Benedek and Scherer, Paul and He, Yixuan and Panagopoulos, George and Riedel, Alexander and Astefanoaei, Maria and Kiss, Oliver and Beres, Ferenc and L\'{o}pez, Guzm\'{a}n and Collignon, Nicolas and Sarkar, Rik},
title = {PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models},
year = {2021},
isbn = {9781450384469},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3459637.3482014},
doi = {10.1145/3459637.3482014},
abstract = {We present PyTorch Geometric Temporal, a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing. The main goal of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easy-to-use framework. PyTorch Geometric Temporal was created with foundations on existing libraries in the PyTorch eco-system, streamlined neural network layer definitions, temporal snapshot generators for batching, and integrated benchmark datasets. These features are illustrated with a tutorial-like case study. Experiments demonstrate the predictive performance of the models implemented in the library on real-world problems such as epidemiological forecasting, ride-hail demand prediction, and web traffic management. Our sensitivity analysis of runtime shows that the framework can potentially operate on web-scale datasets with rich temporal features and spatial structure.},
booktitle = {Proceedings of the 30th ACM International Conference on Information & Knowledge Management},
pages = {4564–4573},
numpages = {10},
keywords = {graph neural networks, machine learning, time series data, deep learning},
location = {Virtual Event, Queensland, Australia},
series = {CIKM '21}
}