stefaniaebli/simplicial_neural_networks
Simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes.
This project helps researchers and data scientists analyze complex relationships in datasets beyond simple pairs. It takes information describing higher-order interactions, like co-authorship networks, and uses it to fill in missing data or understand patterns more deeply. The output provides insights into these complex relationships, for example, imputing missing citations for research papers based on author collaboration structures.
No commits in the last 6 months.
Use this if your data involves interactions among more than two entities at once, such as groups of collaborators, members of a social circle, or components in a biological pathway, and you need to analyze or impute missing information within these higher-order structures.
Not ideal if your data only represents pairwise connections between entities or if you are looking for a simple graph analysis tool without considering higher-order topological features.
Stars
84
Forks
9
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 14, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stefaniaebli/simplicial_neural_networks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE