mims-harvard/SubGNN
Subgraph Neural Networks (NeurIPS 2020)
This project helps researchers and data scientists analyze complex relationships within biological and social networks by classifying or predicting properties of specific groups or modules (subgraphs) within a larger network. It takes in network data, where connections between entities are represented as an edge list, along with predefined subgraphs and their associated labels. The output helps identify disease-related gene pathways or user communities, enabling more targeted interventions or insights for scientists working with network data.
202 stars. No commits in the last 6 months.
Use this if you need to classify or make predictions about specific subnetworks or clusters within a large, interconnected dataset, like identifying disease pathways in a biological network or community structures in social graphs.
Not ideal if your data is not structured as a network or if you are primarily interested in classifying individual nodes or the entire graph, rather than specific subgraphs.
Stars
202
Forks
36
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/SubGNN"
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.
mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in...