feature-attribution 开源项目推荐（55 个）

meta-pytorch /captum

Model interpretability and understanding for PyTorch

mmschlk /shapiq

Shapley Values and Shapley Interactions for Machine Learning

chr5tphr /zennit

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

fzi-forschungszentrum-informatik /TSInterpret

An Open-Source Library for the interpretability of time series classifiers

DFKI-NLP /thermostat

Collection of NLP model explanations and accompanying analysis tools

Julia-XAI /ExplainableAI.jl

Explainable AI in Julia.

ecm200 /caltech_birds

一套笔记本，作为鸟类物种细粒度图像分类过程的指南，使用基于PyTorch的深度神经网络。

jpmorganchase /cf-shap

Counterfactual SHAP: a framework for counterfactual feature importance

AmirhosseinHonardoust /Car-Value-Decomposition-Theory

This article explores the theory behind explainable car pricing using value decomposition, showing how machine learning models can break a predicted price into intuitive components such as brand premium, age depreciation, mileage influence, condition effects, and transmission or fuel-type adjustments.

gsarti /pecore

Materials for "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" at ICLR'24 🐑 🐑

AmirhosseinHonardoust /Tumor-Doppelganger-Studio

乳腺肿瘤样本的相似性优先解释工作室：选择一个病例，找到其最近的“孪生”（良性/恶性相似者），可视化邻里结构，比较特征指纹，并对目标类别进行最小变化的反事实编辑。仅限教育性演示，不用于诊断。

gsarti /lcl23-xnlm-lab

Materials for the Lab "Explaining Neural Language Models from Internal Representations to Model Predictions" at AILC LCL 2023 🔍

hmohebbi /ValueZeroing

The official repo for the EACL 2023 paper "Quantifying Context Mixing in Transformers"

DFKI-NLP /SMV

Code and data for the ACL 2023 NLReasoning Workshop paper "Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods" (Feldhus et al., 2023)

hbaniecki /compress-then-explain

Efficient and accurate explanation estimation with distribution compression (ICLR'25 Spotlight)

rigvedrs /torchxai

Explainability and saliency maps for PyTorch vision models — GradCAM, EigenCAM, Attention Rollout for CNNs, Vision Transformers (ViT), CLIP, YOLO, DETR, DINO. One-line API.

sbrodehl /remotesensing-14-03760

⛈️ Code for the paper "End-to-End Prediction of Lightning Events from Geostationary Satellite Images"

parantapa /integrated-directional-gradients

Implementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.

fspinna /chessplainer

Explain chess positions with SHAP: which pieces make Stockfish think a position is winning, drawn or lost.

BrachioLab /sop

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups