benedekrozemberczki/pytorch_geometric_temporal
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
This project helps researchers and data scientists predict how patterns change over time and space, like forecasting disease spread or predicting web traffic. You input time-series data with connections between different points (a dynamic graph), and it outputs predictions for future states or events within that system. It's designed for anyone working with interconnected data that evolves.
2,962 stars. No commits in the last 6 months.
Use this if you need to build advanced machine learning models for forecasting or analyzing systems where both spatial relationships and temporal changes are critical, such as in logistics, public health, or network management.
Not ideal if your data doesn't have a clear network structure or if the temporal aspect isn't crucial to your predictions.
Stars
2,962
Forks
400
Language
Python
License
MIT
Category
Last pushed
Sep 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/pytorch_geometric_temporal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.