xgfs/verse
Reference implementation of the paper VERSE: Versatile Graph Embeddings from Similarity Measures
Supports multiple similarity measures (PPR, SimRank, Jaccard) through pluggable implementations, with optimized C++ execution and binary compressed sparse row (BCSR) format for memory efficiency. Provides Python bindings for embedding inference alongside the high-performance C++ core, plus format converters for adjacency lists, edge lists, and MATLAB sparse matrices. Outputs node embeddings as binary files compatible with downstream ML frameworks, configurable via command-line parameters for embedding dimensionality, negative sampling, and thread parallelization.
134 stars. No commits in the last 6 months.
Stars
134
Forks
22
Language
C++
License
MIT
Category
Last pushed
Feb 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/xgfs/verse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
eliorc/node2vec
Implementation of the node2vec algorithm.
ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in...