benedekrozemberczki/graph2vec

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

50
/ 100
Established

Leverages Weisfeiler-Lehman graph kernels for unsupervised feature extraction across WL iterations, then applies gensim's Skip-gram model with multi-worker parallelization to learn fixed-length graph embeddings. Accepts JSON-formatted graph datasets with edge lists and optional node features, outputting task-agnostic embeddings suitable for graph classification, clustering, and downstream supervised tasks without manual feature engineering.

933 stars. No commits in the last 6 months.

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.