facebookresearch/taser-tgnn
[IPDPS 2024] Adaptive neighbor sampling for temporal GNN
This project helps machine learning engineers and researchers accelerate the training of graph neural networks (GNNs) on datasets that evolve over time. It takes in dynamic graph data, such as interactions on social networks or transaction histories, and outputs optimized graph representations that can be used for tasks like link prediction or anomaly detection. The end user is a machine learning practitioner working with large, time-sensitive graph datasets.
No commits in the last 6 months.
Use this if you are a machine learning engineer dealing with large, constantly changing graph data and need to train GNNs more efficiently and accurately on GPU.
Not ideal if your graph data is static or small, or if you are not working with graph neural networks.
Stars
16
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/facebookresearch/taser-tgnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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.