Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
| Date | Stars |
|---|---|
| 2026-07-24 | 2991 |
| 2026-07-25 | 2992 |
| 2026-07-28 | 2992 |
| 2026-07-30 | 2992 |
| 2026-07-31 | 2993 |
| 2026-08-06 | 2994 |
Today
+1 stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.07%/day
[pypi-image]: https://badge.fury.io/py/torch-geometric-temporal.svg [pypi-url]: https://pypi.python.org/pypi/torch-geometric-temporal [size-image]: https://img.shields.io/github/repo-size/benedekrozemberczki/pytorch_geometric_temporal.svg [size-url]: https://github.com/benedekrozemberczki/pytorch_geometric_temporal/archive/master.zip [build-image]: https://github.com/benedekrozemberczki/pytorch_geometric_temporal/workflows/CI/badge.svg [build-url]: https://github.com/benedekrozemberczki/pytorch_geometric_temporal/actions?query=workflow%3ACI [docs-image]: https://readthedocs.org/projects/pytorch-geometric-temporal/badge/?version=latest [docs-url]: https://pytorch-geometric-temporal.readthedocs.io/en/latest/?badge=latest [coverage-image]: https://codecov.io/gh/benedekrozemberczki/pytorch_geometric_temporal/branch/master/graph/badge.svg [coverage-url]: https://codecov.io/github/benedekrozemberczki/pytorch_geometric_temporal?branch=master <p align="center"> <img width="90%" src="https://raw.githubusercontent.com/benedekrozemberczki/pytorch_geometric_temporal/master/docs/source/_static/img/text_logo.jpg?sanitize=true" /> </p> ----------------------------------------------------- [![PyPI Version][pypi-image]][pypi-url] [![Docs Status][docs-image]][docs-url] [![Build Status][build-image]][build-url] [](https://arxiv.org/abs/2104.07788) [](https://arxiv.org/abs/2507.11683) [](https://twitter.com/intent/follow?screen_name=benrozemberczki) <!-- [![Code Coverage][coverage-image]][coverage-url] --> **[Documentation](https://pytorch-geometric-temporal.readthedocs.io)** | **[External Resources](https://pytorch-geometric-temporal.readthedocs.io/en/latest/notes/resources.html)** | **[Datasets](https://pytorch-geometric-temporal.readthedocs.io/en/latest/notes/introduction.html#discrete-time-datasets)** *PyTorch Geometric Temporal* is a temporal (dynamic) extension library for [PyTorch Geometric](https://github.com/rusty1s/pytorch_geometric). <p align="justify">The library consists of various dynamic and temporal geometric deep learning, embedding, and spatio-temporal regression methods from a variety of published research papers. Moreover, it comes with an easy-to-use dataset loader, train-test splitter and temporal snaphot iterator for dynamic and temporal graphs. The framework naturally provides GPU support. It also comes with a number of benchmark datasets from the epidemological forecasting, sharing economy, energy production and web traffic management domains. Finally, you can also create your own datasets.</p> PyTorch Geometric Temporal now includes support for index-batching - a new batching technique that improves spatiotemporal memory efficiency without any impact on accuracy. Take a look at [the index-batching examples](https://github.com/benedekrozemberczki/pytorch_geometric_temporal/tree/master/examples/indexBatching), which allow users to easily customize training to their needs and scale to larger datasets than previously possible. Additionally, PyTorch Geometric Temporal supports memory-efficient distributed data parallel training using Dask-DDP in combination with index-batching. The package interfaces well with [Pytorch Lightning](https://pytorch-lightning.readthedocs.io) which allows training on CPUs, single and multiple GPUs out-of-the-box. Take a look at this [introductory example](https://github.com/benedekrozemberczki/pytorch_geometric_temporal/blob/master/examples/recurrent/lightning_example.py) of using PyTorch Geometric Temporal with Pytorch Lightning. We also provide detailed examples for each of the [recurrent](https://github.com/benedekrozemberczki/pytorch_geometric_temporal/tree/master/examples/recurrent) models and [notebooks](https://github.com/benedekrozemberczki/pyto
Excerpt of 16,157 characters
Read on GitHub
Benedek Rozemberczki · @google · United Kingdom
1.6k
174
93
44
19
James Myatt · United Kingdom
15
13
7
Olivér Kiss · @spreadmonitor · Hungary
6
5
Andreas Fehlner · Germany
4
4
Domenico Tortorella · University of Pisa · Italy
3
3
2
2
2
2
Sean Ye · Georgia Tech
2
Joaquin Cabezas · Adevinta · Spain
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2c7056f4dfb0f853, topic:deep-learning, topic:pytorch, readme:data parallel