explainability topic

📍 Interactive Studio for Explanatory Model Analysis

ModelOriented

Papers about explainability of GNNs

flyingdoog

💡 Adversarial attacks on explanations and how to defend them

hbaniecki

Visualization tool for Graph Neural Networks

dmlc

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.

hate-alert

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

MAIF

Official implementation of Score-CAM in PyTorch

haofanwang

Training & evaluation library for text-based neural re-ranking and dense retrieval models built with PyTorch

sebastian-hofstaetter

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

csinva

A game theoretic approach to explain the output of any machine learning model.

shap