Affinis: tools for inferring relations from co-occurrence data
Affinis is a tool for assisting in unsupervised structure learning on sparse, binary data. For large (sparse) feature matrices, especially ones with binary-valued entries, techniques to figure out the underlying structure of the feature space are widely varied, and different communities have widely different practices and assumptions for what is an appropriate approach. Affinis provides reference implementations for many of these methods, with a consistent API to enable community adoption and a shared benchmarking environment.
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| accrualPeriodicity | irregular |
| bureauCode |
[ "006:55" ] |
| contactPoint |
{ "fn": "Rachael Sexton", "hasEmail": "mailto:rachael.sexton@nist.gov" } |
| description | Affinis is a tool for assisting in unsupervised structure learning on sparse, binary data. For large (sparse) feature matrices, especially ones with binary-valued entries, techniques to figure out the underlying structure of the feature space are widely varied, and different communities have widely different practices and assumptions for what is an appropriate approach. Affinis provides reference implementations for many of these methods, with a consistent API to enable community adoption and a shared benchmarking environment. |
| distribution |
[ { "title": "Code Repository", "format": "plain-text, python code", "accessURL": "https://github.com/usnistgov/affinis", "description": "via USNISTGOV organization on GitHub" }, { "title": "README", "format": "markdown", "mediaType": "text/markdown", "downloadURL": "https://data.nist.gov/od/ds/mds2-4107/README-affinis.md" } ] |
| identifier | ark:/88434/mds2-4107 |
| issued | 2026-05-08 |
| keyword |
[ "binary data", "covariance shrinkage", "edge prediction", "feature learning", "filtering", "graph theory", "multi-label", "network analysis", "scientific-software", "sparse matrix", "structure learning", "tools" ] |
| landingPage | https://data.nist.gov/od/id/mds2-4107 |
| language |
[ "en" ] |
| license | https://www.nist.gov/open/license |
| modified | 2026-02-17 00:00:00 |
| programCode |
[ "006:045" ] |
| publisher |
{ "name": "National Institute of Standards and Technology", "@type": "org:Organization" } |
| theme |
[ "Information Technology:Complex systems", "Information Technology:Computational science", "Information Technology:Data and informatics", "Manufacturing:Systems engineering", "Mathematics and Statistics:Mathematical knowledge management", "Mathematics and Statistics:Modeling and simulation research", "Mathematics and Statistics:Numerical methods and software", "Mathematics and Statistics:Statistical analysis", "Mathematics and Statistics:Uncertainty quantification" ] |
| title | Affinis: tools for inferring relations from co-occurrence data |
