#Interpretability

Showing 60 of 85 repositories tagged #interpretability, ranked by stars

shap
shap
shap

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

Score
100
โ˜… 25.6k โ‘‚ 3.7k +15/day
Jupyter Notebook
EthicalML
EthicalML
awesome-production-machine-learning

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

Score
98
โ˜… 20.7k โ‘‚ 2.6k +19/day
jacobgil
jacobgil
pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Score
100
โ˜… 12.9k โ‘‚ 1.7k +8/day
Python
interpretml
interpretml
interpret

Fit interpretable models. Explain blackbox machine learning.

Score
95
โ˜… 6.9k โ‘‚ 783 +2/day
C++
meta-pytorch
meta-pytorch
captum

Model interpretability and understanding for PyTorch

Score
86
โ˜… 5.7k โ‘‚ 560 +5/day
Python
tensorflow
tensorflow
lucid

A collection of infrastructure and tools for research in neural network interpretability.

Score
86
โ˜… 4.7k โ‘‚ 647 โ€”
Jupyter Notebook
jphall663
jphall663
awesome-machine-learning-interpretability

A curated list of awesome responsible machine learning resources.

Score
71
โ˜… 4.0k โ‘‚ 628 +2/day
MAIF
MAIF
shapash

๐Ÿ”… Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Score
57
โ˜… 3.2k โ‘‚ 388 +8/day
Jupyter Notebook
stellargraph
stellargraph
stellargraph

StellarGraph - Machine Learning on Graphs

Score
14
โ˜… 3.1k โ‘‚ 442 โ€”
Python
SeldonIO
SeldonIO
alibi

Algorithms for explaining machine learning models

Score
91
โ˜… 2.6k โ‘‚ 264 โ€”
Python
frgfm
frgfm
torch-cam

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)

Score
93
โ˜… 2.3k โ‘‚ 224 +1/day
Python
chaoyanghe
chaoyanghe
Awesome-Federated-Learning

FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai

Score
77
โ˜… 2.0k โ‘‚ 332 โ€”
google-deepmind
google-deepmind
penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

Score
76
โ˜… 1.9k โ‘‚ 70 โ€”
Python
microsoft
microsoft
responsible-ai-toolbox

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.

Score
100
โ˜… 1.8k โ‘‚ 484 โ€”
TypeScript
ramprs
ramprs
grad-cam

[ICCV 2017] Torch code for Grad-CAM

Score
73
โ˜… 1.7k โ‘‚ 236 โ€”
Lua
csinva
csinva
imodels

Interpretable ML package ๐Ÿ” for concise, transparent, and accurate predictive modeling (sklearn-compatible).

Score
95
โ˜… 1.6k โ‘‚ 138 +2/day
Jupyter Notebook
ModelOriented
ModelOriented
DALEX

moDel Agnostic Language for Exploration and eXplanation

Score
90
โ˜… 1.5k โ‘‚ 169 +1/day
Python
cdpierse
cdpierse
transformers-interpret

Model explainability that works seamlessly with ๐Ÿค— transformers. Explain your transformers model in just 2 lines of code.

Score
68
โ˜… 1.4k โ‘‚ 100 โ€”
Jupyter Notebook
EthicalML
EthicalML
xai

XAI - An eXplainability toolbox for machine learning

Score
80
โ˜… 1.3k โ‘‚ 186 +3/day
Python
sicara
sicara
tf-explain

Interpretability Methods for tf.keras models with Tensorflow 2.x

Score
71
โ˜… 1.0k โ‘‚ 110 โ€”
Python
ndif-team
ndif-team
nnsight

The nnsight package enables interpreting and manipulating the internals of deep learned models.

Score
43
โ˜… 981 โ‘‚ 98 +4/day
Python
hila-chefer
hila-chefer
Transformer-MM-Explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

Score
67
โ˜… 911 โ‘‚ 116 +1/day
Jupyter Notebook
oneTaken
oneTaken
awesome_deep_learning_interpretability

ๆทฑๅบฆๅญฆไน ่ฟ‘ๅนดๆฅๅ…ณไบŽ็ฅž็ป็ฝ‘็ปœๆจกๅž‹่งฃ้‡Šๆ€ง็š„็›ธๅ…ณ้ซ˜ๅผ•็”จ/้กถไผš่ฎบๆ–‡(้™„ๅธฆไปฃ็ )

Score
61
โ˜… 767 โ‘‚ 123 โ€”
mmschlk
mmschlk
shapiq

Shapley Interactions and Shapley Values for Machine Learning

Score
29
โ˜… 753 โ‘‚ 66 +3/day
Python
MisaOgura
MisaOgura
flashtorch

Visualization toolkit for neural networks in PyTorch! Demo -->

Score
57
โ˜… 743 โ‘‚ 88 โ€”
HTML
tensorflow
tensorflow
decision-forests

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.

Score
89
โ˜… 693 โ‘‚ 117 โ€”
Python
jphall663
jphall663
interpretable_machine_learning_with_python

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

Score
62
โ˜… 682 โ‘‚ 206 โ€”
Jupyter Notebook
understandable-machine-intelligence-lab
understandable-machine-intelligence-lab
Quantus

[JMLR 2023] Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

Score
84
โ˜… 668 โ‘‚ 91 +1/day
Jupyter Notebook
google
google
yggdrasil-decision-forests

A library to train, evaluate, interpret, and productionize decision forest models such as Random Forest and Gradient Boosted Decision Trees.

Score
0
โ˜… 662 โ‘‚ 80 +1/day
C++
tensorflow
tensorflow
tcav

Code for the TCAV ML interpretability project

Score
86
โ˜… 653 โ‘‚ 147 +1/day
Jupyter Notebook
ScalaConsultants
ScalaConsultants
Aspect-Based-Sentiment-Analysis

๐Ÿ’ญ Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)

Score
82
โ˜… 584 โ‘‚ 94 โ€”
Python
linkedin
linkedin
FastTreeSHAP

Fast SHAP value computation for interpreting tree-based models

Score
50
โ˜… 558 โ‘‚ 38 โ€”
Python
BCG-X-Official
BCG-X-Official
facet

Human-explainable AI.

Score
81
โ˜… 533 โ‘‚ 47 โ€”
Jupyter Notebook
h2oai
h2oai
mli-resources

H2O.ai Machine Learning Interpretability Resources

Score
48
โ˜… 490 โ‘‚ 129 โ€”
Jupyter Notebook
inseq-team
inseq-team
inseq

Interpretability for sequence generation models ๐Ÿ› ๐Ÿ”

Score
100
โ˜… 470 โ‘‚ 42 +1/day
Python
TuGraph-family
TuGraph-family
chat2graph

Chat2Graph: Graph Native Agentic System.

Score
88
โ˜… 424 โ‘‚ 53 โ€”
Python
IAAR-Shanghai
IAAR-Shanghai
Awesome-Attention-Heads

An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

Score
50
โ˜… 412 โ‘‚ 12 +2/day
TeX
pratyushasharma
pratyushasharma
laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Score
62
โ˜… 395 โ‘‚ 35 +1/day
Python
sergioburdisso
sergioburdisso
pyss3

A Python library for Interpretable Machine Learning in Text Classification using the SS3 model, with easy-to-use visualization tools for Explainable AI :octocat:

Score
64
โ˜… 349 โ‘‚ 44 +1/day
Python
ModelOriented
ModelOriented
modelStudio

๐Ÿ“ Interactive Studio for Explanatory Model Analysis

Score
43
โ˜… 333 โ‘‚ 33 โ€”
R
SteveKGYang
SteveKGYang
MentalLLaMA

This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.

Score
38
โ˜… 322 โ‘‚ 39 +3/day
Python
rigvedrs
rigvedrs
YOLO-26-CAM

Wanna know what your model sees? Here's a package for applying EigenCAM (like GradCAM) and generating heatmap from the new YOLO models

Score
75
โ˜… 308 โ‘‚ 59 +2/day
Jupyter Notebook
JoaoLages
JoaoLages
diffusers-interpret

Diffusers-Interpret ๐Ÿค—๐Ÿงจ๐Ÿ•ต๏ธโ€โ™€๏ธ: Model explainability for ๐Ÿค— Diffusers. Get explanations for your generated images.

Score
41
โ˜… 278 โ‘‚ 14 โ€”
Jupyter Notebook
yewsiang
yewsiang
ConceptBottleneck

Concept Bottleneck Models, ICML 2020

Score
45
โ˜… 253 โ‘‚ 45 โ€”
Python
haofanwang
haofanwang
Awesome-Computer-Vision

Awesome Resources for Advanced Computer Vision Topics

Score
43
โ˜… 248 โ‘‚ 47 +1/day
guidelabs
guidelabs
steerling

Interpretable Causal Diffusion Language Models

Score
75
โ˜… 231 โ‘‚ 14 +2/day
Python
pralab
pralab
secml

A Python library for Secure and Explainable Machine Learning

Score
39
โ˜… 192 โ‘‚ 27 โ€”
Jupyter Notebook
csinva
csinva
imodelsX

Interpret text data with LLMs (sklearn compatible).

Score
70
โ˜… 176 โ‘‚ 27 โ€”
Python
pietrobarbiero
pietrobarbiero
pytorch_explain

PyTorch Explain: Interpretable Deep Learning in Python.

Score
32
โ˜… 174 โ‘‚ 17 โ€”
Jupyter Notebook
zjunlp
zjunlp
KnowledgeCircuits

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Score
52
โ˜… 172 โ‘‚ 11 โ€”
Python
poloclub
poloclub
timbertrek

Explore and compare 1K+ accurate decision trees in your browser!

Score
29
โ˜… 169 โ‘‚ 11 โ€”
TypeScript
whyisyoung
whyisyoung
CADE

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

Score
34
โ˜… 148 โ‘‚ 41 โ€”
Python
interpretml
interpretml
gam-changer

Editing machine learning models to reflect human knowledge and values

Score
24
โ˜… 131 โ‘‚ 12 +1/day
JavaScript
laura-rieger
laura-rieger
deep-explanation-penalization

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

Score
27
โ˜… 127 โ‘‚ 14 โ€”
Jupyter Notebook
csinva
csinva
hierarchical-dnn-interpretations

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" ๐Ÿง  (ICLR 2019)

Score
30
โ˜… 126 โ‘‚ 21 โ€”
Jupyter Notebook
Alsace08
Alsace08
Chain-of-Embedding

[ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"

Score
0
โ˜… 101 โ‘‚ 8 +1/day
Python
ModelOriented
ModelOriented
treeshap

Compute SHAP values for your tree-based models using the TreeSHAP algorithm

Score
66
โ˜… 99 โ‘‚ 24 +1/day
R
alstonlo
alstonlo
torch-influence

A simple PyTorch implementation of influence functions.

Score
18
โ˜… 96 โ‘‚ 11 โ€”
Python
alanqrwang
alanqrwang
keymorph

Robust multimodal image registration via keypoints

Score
25
โ˜… 94 โ‘‚ 21 โ€”
Python
snehankekre
snehankekre
streamlit-shap

streamlit-shap provides a wrapper to display SHAP plots in Streamlit.

Score
16
โ˜… 94 โ‘‚ 10 +1/day
Python
Related Topics
#machine-learning#deep-learning#explainable-ai#explainability#python#pytorch#xai#explainable-ml#interpretable-machine-learning#data-science#artificial-intelligence#tensorflow

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly