benedekrozemberczki/graph2vec
A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).
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.
Stars
933
Forks
168
Language
Python
License
GPL-3.0
Category
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.
Related tools
Accenture/AmpliGraph
Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org
DeepGraphLearning/graphvite
GraphVite: A General and High-performance Graph Embedding System
bi-graph/Emgraph
A Python library for knowledge graph representation learning (graph embedding).
nju-websoft/muKG
μKG: A Library for Multi-source Knowledge Graph Embeddings and Applications, ISWC 2022
zjunlp/KNN-KG
[NLPCC 2023] Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings with...