72 Open Source Xai Software Projects

Fit interpretable models. Explain blackbox machine learning.

In-Database Machine Learning

A curated list of awesome machine learning interpretability resources.

Algorithms for explaining machine learning models

Interpretability and explainability of data and machine learning models

moDel Agnostic Language for Exploration and eXplanation

XAI - An eXplainability toolbox for machine learning

Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.

Interesting resources related to XAI (Explainable Artificial Intelligence)

H2O.ai Machine Learning Interpretability Resources

Generate Diverse Counterfactual Explanations for any machine learning model.

A Python package implementing a new interpretable machine learning model for text classification (with visualization tools for Explainable AI :octocat:)

Layer-wise Relevance Propagation (LRP) for LSTMs

📍 Interactive Studio for Explanatory Model Analysis

Pytorch Implementation of recent visual attribution methods for model interpretability

Model Agnostics breakDown plots

A curated list of awesome Fairness in AI resources

Explanatory Model Analysis. Explore, Explain and Examine Predictive Models

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.

Break Down with interactions for local explanations (SHAP, BreakDown, iBreakDown)

Model verification, validation, and error analysis

Detect model's attention

Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.

FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)

Fast approximate Shapley values in R

Local Interpretable (Model-agnostic) Visual Explanations - model visualization for regression problems and tabular data based on LIME method. Available on CRAN

Minimal starting point for rapid prototyping interactive Human-AI tools

Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

Repository for the Explainable Deep One-Class Classification paper

Surrogate Assisted Feature Extraction in R

The Machine Learning Toybox for testing the behavior of autonomous agents.

Slides, videos and other potentially useful artifacts from various presentations on responsible machine learning.

Data generator for Arena - interactive XAI dashboard

Implementation of the Anchors algorithm: Explain black-box ML models

💡 Adversarial attacks on model explanations, and evaluation approaches

Variable importance via oscillations

In this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

Model Agnostic Counterfactual Explanations

Article for Special Edition of Information: Machine Learning with Python

A collection of research materials on explainable AI/ML

Visualize correlations between variables

CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox

COVID-Net Open Source Initiative - Models and Data for COVID-19 Detection in Chest CT

Visualization tool for Graph Neural Networks

Code for our USENIX Security 2021 paper -- CADE: Detecting and Explaining Concept Drift Samples for Security Applications

[CVPR2021] "Visualizing Adapted Knowledge in Domain Transfer". Visualization for domain adaptation. #explainable-ai

A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).

👋 Xplique is a Neural Networks Explainability Toolbox

Machine Learning in one line of code

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Adaptive, interpretable wavelets across domains (NeurIPS 2021)

Quantitative Testing with Concept Activation Vectors in PyTorch

Awesome Explainable AI (XAI) and Interpretable ML Papers and Resources

A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.

Deep Logic is a python package providing a set of utilities to build deep learning models that are explainable by design.

Code to reproduce our paper on probabilistic algorithmic recourse: https://arxiv.org/abs/2006.06831

Official Implementation of Remembering for the Right Reasons (ICLR 2021)

Interactive XAI dashboard

General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems

Genetic programming method for explaining complex black-box models

An intuitive platform for deploying the latest discoveries in healthcare AI to everybody's phones. Powered by PyTorch!

Case Study course for DS studies in Summer 2020/2021

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification".

Papers about explainability of GNNs

A diff tool for language models

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

Learning clinical-decision rules with interpretable models.

Trained Neural Networks (LSTM, HybridCNN/LSTM, PyramidCNN, Transformers, etc.) & comparison for the task of Hate Speech Detection on the OLID Dataset (Tweets).