Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in
Algorithms for explaining machine learning models
Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training inherently transparent models and applying post-hoc explanation techniques to make machine learning predictions human-understandable. The framework distinguishes itself by integrating differential privacy into the training of interpretable models to prevent sensitive data from leaking through explanations. It also features a visualization tool for rendering interactive decision paths and model behavior. The library covers model explainability through feature importance calcu
(a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks)
Leave One Feature Out Importance
The main features of aerdem4/lofo-importance are: Explainability and Fairness, Explainable AI Libraries, Model Interpretability.
Open-source alternatives to aerdem4/lofo-importance include: seldonio/alibi — Algorithms for explaining machine learning models. pytorch/captum — Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and… interpretml/interpret — Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training… csinva/imodels — Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible). austinrochford/pycebox — ⬛ Python Individual Conditional Expectation Plot Toolbox. ankurtaly/integrated-gradients — (a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks).