ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
This project helps researchers and data scientists understand how relationships evolve over time within dynamic networks, such as social media interactions or evolving collaboration graphs. It takes a stream of network events (like new connections or interactions) and produces numerical representations (embeddings) for each node, reflecting its current role and connections. This allows for tasks like identifying similar users or predicting future connections in real-time. It is designed for network scientists and data analysts working with changing relational data.
No commits in the last 6 months. Available on PyPI.
Use this if you need to analyze and find patterns in networks where connections and relationships change frequently and you want up-to-date node representations.
Not ideal if your network data is static and does not change over time, or if you are not interested in the temporal evolution of relationships.
Stars
57
Forks
12
Language
Jupyter Notebook
License
CC0-1.0
Category
Last pushed
Jan 12, 2022
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ferencberes/online-node2vec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
eliorc/node2vec
Implementation of the node2vec algorithm.
mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in...
mims-harvard/Raindrop
Graph Neural Networks for Irregular Time Series