Open-source alternatives to What If Tool

Leave One Feature Out Importance

This project is an agnostic model interpretability framework and explainability tool designed to provide local interpretable explanations for individual predictions. It functions as a local surrogate model that approximates the behavior of any machine learning classifier or regression model to identify the most influential features for a specific instance. The framework is designed to be model-agnostic, meaning it can explain predictions across tabular, text, and image data regardless of the underlying architecture. It employs local linear approximations and feature importance visualization t

SHAP is a machine learning explainer that uses a game-theoretic framework to estimate the contribution of each feature to a model prediction. It provides a set of tools for quantifying how individual input features push a specific output away from a baseline value. The project includes specialized explainers for different architectures, including high-speed implementations for decision trees and ensemble models, linearization algorithms for deep learning networks, and covariance integration for linear models. It also features a model-agnostic interpretability tool that uses a kernel method to

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

Python implementation of the rulefit algorithm

📰 Latest News 📰 - 🗡️ What is HarmBench 🛡️ - 🌐 Overview 🌐 - ☕ Quick Start ☕ - ⚙️ Installation - 🛠️ Running the Evaluation Pipeline - ➕ Using your own models in HarmBench - ➕ Using your own red teaming methods in HarmBench - 🤗 Classifiers - ⚓ Documentation ⚓ - 🌱 HarmBench's Roadmap 🌱 -…

Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.

Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

(a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks)

This repository contains a sample implementation of Gradient Feature Auditing (GFA) meant to be generalizable to most datasets. For more information on the repair process, see our paper on Certifying and Removing Disparate Impact. For information on the full auditing process, see our paper on…

WeightWatcher (WW) is an open-source, diagnostic tool for analyzing Deep Neural Networks (DNN), without needing access to training or even test data. It is based on theoretical research into Why Deep Learning Works, based on our Theory of Heavy-Tailed Self-Regularization (HT-SR). It uses ideas…

XAI - An eXplainability toolbox for machine learning

A Tree based feature selection tool which combines both the Boruta feature selection algorithm with shapley values.

The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

Explain & debug any blackbox machine learning model with a single line of code.

A framework for Privacy Preserving Machine Learning

TreeInterpreter

NeuroX provide all the necessary tooling to perform Interpretation and Analysis of (Deep) Neural Networks centered around Probing. Specifically, the toolkit provides:

TorchCAM: class activation explorer

effector an eXplainable AI package for tabular data. It:

Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl

Interpretability and explainability of data and machine learning models

This repo contains the code for our talk "Demystifying the neural network black box". Slides are available on Speaker Deck. This code has not been maintained for over a year. It's archived on 2024-12-18.

Bias Auditing & Fair ML Toolkit