feature-attribution

There are 2 repositories under feature-attribution topic.

pytorch / captum
Model interpretability and understanding for PyTorch
feature-attribution feature-importance interpretability interpretable-ai interpretable-ml
Language:Python 5404
shapiq
mmschlk / shapiq
Shapley Interactions and Shapley Values for Machine Learning
python feature-interactions explainability interpretability machine-learning shap shapley shapiq shapley-interactions banzhaf-index explainable-ai feature-importance game-theory interpretable-machine-learning feature-attribution
Language:Python 612
chr5tphr / zennit
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
lrp pytorch xai machine-learning attribution explainability python interpretability explainable-ai interpretable-ai feature-attribution interpretable-ml deep-learning
Language:Python 220
DFKI-NLP / thermostat
Collection of NLP model explanations and accompanying analysis tools
explainability interpretability natural-language-processing transformers datasets feature-attribution saliency-maps heatmaps captum explainable-nlp
Language:Jsonnet 145
fzi-forschungszentrum-informatik / TSInterpret
An Open-Source Library for the interpretability of time series classifiers
counterfactual-explanations explainable-ai explainable-artificial-intelligence explainable-ml feature-attribution interpretability interpretable-machine-learning interpretable-ml time-series
Language:Python 132
Julia-XAI / ExplainableAI.jl
Explainable AI in Julia.
xai lrp interpretability interpretable-ai feature-attribution julia attribution-methods explainable-ai
Language:Julia 111
caltech_birds
ecm200 / caltech_birds
A set of notebooks as a guide to the process of fine-grained image classification of birds species, using PyTorch based deep neural networks.
activation-maximization caltech-birds classification-model cnn cub-200-2011 deep-learning deep-neural-networks feature-attribution image-classification machine-learning manifold-learning pytorch pytorch-tutorial
Language:Jupyter Notebook 45
jpmorganchase / cf-shap
Counterfactual SHAP: a framework for counterfactual feature importance
explainability explainable-ai explainable-artificial-intelligence explainable-ml explanations feature-attribution feature-importance machine-learning shap shapley shapley-values tree-based xgboost algorithmic-recourse counterfactual-explanations counterfactuals facct2022 explainable-machine-learning
Language:HTML 20
gsarti / pecore
Materials for "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" at ICLR'24 🐑 🐑
document-level-nmt explainable-ai feature-attribution interpretability language-model large-language-models machine-translation
Language:Jupyter Notebook 14
gsarti / lcl23-xnlm-lab
Materials for the Lab "Explaining Neural Language Models from Internal Representations to Model Predictions" at AILC LCL 2023 🔍
ailc diagnostic-classifiers feature-attribution ferret inseq interpretability lab probing-task transformers tutorial xai
Language:Jupyter Notebook 13
hmohebbi / ValueZeroing
The official repo for the EACL 2023 paper "Quantifying Context Mixing in Transformers"
attention-mechanism contextualized-representation feature-attribution interpretability pre-trained-language-models transformers
Language:Python 12
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)
chatgpt explainability explainable-nlp feature-attribution integrated-gradients interpretability saliency-maps saliency-methods text-classification transformers
Language:Python 10
sbrodehl / remotesensing-14-03760
⛈️ Code for the paper "End-to-End Prediction of Lightning Events from Geostationary Satellite Images"
class-imbalance feature-attribution machine-learning meteorology neural-networks nowcasting satellite-imagery lightning-prediction short-term-forecasts
Language:Python 9
parantapa / integrated-directional-gradients
Implementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.
interpretability feature-importance interpretable-ai interpretable-ml feature-attribution
Language:Python 7
hbaniecki / compress-then-explain
Efficient and accurate explanation estimation with distribution compression (ICLR 2025 Spotlight)
explainable-ai interpretable-machine-learning sage shap goodpoints kernel-thinning dalex feature-attribution pdp
Language:Python 6
KurtButler / 2024_attributions_paper
Reproducible code for our paper "Explainable Learning with Gaussian Processes"
explainable-ai feature-attribution gaussian-processes integrated-gradients sparse-approximations
Language:MATLAB 3
FilomKhash / Tree-based-paper
Codes for the paper On marginal feature attributions of tree-based models
feature-attribution tree-based-methods
Language:Jupyter Notebook 2
yuasosnin / financial-market-shap
Bachelor's thesis for degree in Economics at HSE University, Saint-Petersburg (2022)
deep-learning feature-attribution stock-price-prediction financial-machine-learning
Language:Jupyter Notebook 2
hbaniecki / robust-feature-effects
Robustness of Global Feature Effect Explanations (ECML PKDD 2024)
dalex explainable-ai explainable-machine-learning explanatory-model-analysis feature-attribution iml interpretable-machine-learning partial-dependence-plot accumulated-local-effects
Language:Jupyter Notebook 1
kennethsible / confidence-estimation
Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages
confidence-estimation feature-attribution machine-translation
Language:Python 0
RiSchmi / MLbased_spatial_pollution_prediction
NO2 Prediction: Performance and Robustness Comparison between Random Forest and Graph Neural Network
2023 berlin comparison feature-attribution graph-algorithms graph-neural-network pollution-prediction r2-score random-forest shapely no2-prediction
Language:Jupyter Notebook 0
Animadversio / Neuronal_Feature_Attribution_Model
Feature Attribution methods for neurons and Evolution experiments
cnn evolutionary-algorithms feature-attribution interpretable-machine-learning nmf-decomposition
Language:Jupyter Notebook
jingyan-li / TrafficForecastUnetInterpret-Python
Understanding the UNet for Traffic Forecasting Task - A Visual Analytics Approach
feature-attribution traffic-forecasting unet
Language:Jupyter Notebook