mateoespinosa/tabcbm
Official Implementation of TMLR's paper: "TabCBM: Concept-based Interpretable Neural Networks for Tabular Data"
This project helps data scientists, machine learning engineers, and researchers analyze complex tabular datasets, especially in fields like healthcare or genomics. It takes your raw tabular data and generates accurate predictions, but critically, it also explains *why* it made those predictions by identifying high-level 'concepts' within the data. This means you get both a reliable outcome and a clear understanding of the underlying factors influencing it.
No commits in the last 6 months.
Use this if you need a machine learning model for tabular data that not only performs well but also provides clear, human-understandable explanations for its predictions, even without explicit concept labels in your training data.
Not ideal if your primary concern is only raw predictive performance on non-tabular data or if you have no need for interpretable, concept-based explanations.
Stars
15
Forks
2
Language
Python
License
MIT
Last pushed
Apr 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mateoespinosa/tabcbm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...