microsoft/figure

[NeurIPS 2023, KDD MLG 2023] Repo that contains code for the paper titled: "FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations".

33
/ 100
Emerging

This project helps machine learning researchers and data scientists working with graph-structured data. It takes raw graph data and produces highly effective, low-dimensional numerical representations (embeddings) for each 'node' or entity within the graph. These embeddings can then be used to improve performance on downstream tasks like classification or link prediction.

No commits in the last 6 months.

Use this if you need to generate high-quality, efficient node embeddings from graph data for various machine learning tasks, especially if you're exploring alternatives to traditional contrastive learning methods.

Not ideal if you are looking for a plug-and-play solution without any coding or if your primary interest is not in advancing graph representation learning research.

graph-neural-networks node-embeddings unsupervised-learning graph-data-science representation-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

MIT

Last pushed

Jul 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/figure"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.