Popular GitHub Repositories for Interpretable Deep Learning

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

Tensorflow tutorial for various Deep Neural Network visualization techniques

PyTorch Explain: Interpretable Deep Learning in Python.

Pytorch Implementation of recent visual attribution methods for model interpretability

Protein-compound affinity prediction through unified RNN-CNN

Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks

Official code for the ICML 2021 paper "Generative Causal Explanations for Graph Neural Networks."

Multislice PHATE for tensor embeddings

Official repository of cross-modal transformer for interpretable automatic sleep stage classification. https://arxiv.org/abs/2208.06991

Time series explainability via self-supervised model behavior consistency

Extracting knowledge graphs from language models as a diagnostic benchmark of model performance (NeurIPS XAI 2021).

Unsupervised Representation Learning for Singing Voice Separation

?B nets: learning discrete, boolean-valued functions by gradient descent

Implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation (Fong, et. al., 2018)

Deep learning for personalized interpretability for compositional health data

ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots

Reproducing Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet using LLaMA. This project explores monosemantic neurons in large language models, implementing and extending methods to scale and analyze interpretability in LLaMA-based architectures.

Interpretability and Fairness in Machine Learning

An unofficial version of the PyTorch implementation of CURE and Fast Adversarial training with FGSM.

Explainable audio speech embeddings enhance emotion detection for low-resource setting