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".
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.
Stars
11
Forks
2
Language
Python
License
MIT
Category
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.
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.