benedekrozemberczki/graph2vec

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

50
/ 100
Established

This project helps scientists, researchers, or anyone working with complex network data analyze entire graphs. You provide a folder of graph structures (like molecular diagrams, social networks, or brain connectivity maps), and it generates fixed-length numerical descriptions for each graph. These descriptions allow you to compare, classify, or cluster whole graphs, rather than just individual parts.

933 stars. No commits in the last 6 months.

Use this if you need to represent entire graphs as numerical vectors for tasks like classification or clustering, and you want an automated, data-driven approach instead of handcrafted features.

Not ideal if your primary goal is to analyze individual nodes or substructures within a single graph, rather than comparing and categorizing whole graphs.

graph-classification network-analysis cheminformatics social-network-analysis materials-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

933

Forks

168

Language

Python

License

GPL-3.0

Last pushed

Nov 06, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/benedekrozemberczki/graph2vec"

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