sashakolpakov/graphem-rapids
Graph embedding for influence maximization in networks
Implements force-directed layout with geometric intersection detection to produce embeddings that correlate with centrality measures. Dual PyTorch and RAPIDS cuVS backends enable automatic scaling from 1K to 1M+ vertices with GPU acceleration, memory-efficient chunking, and CPU fallback. Provides scipy-sparse matrix input, sklearn-style parameters, built-in graph generators (Erdős-Rényi, scale-free, SBM), and embedding-based seed selection for influence maximization via Independent Cascade evaluation.
Available on PyPI.
Stars
4
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 22, 2025
Monthly downloads
13
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sashakolpakov/graphem-rapids"
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...