Explaining black boxes with a SMILE: Statistical Mode-agnostic Interpretability with Local Explanations
-
Updated
May 31, 2024 - Python
Explaining black boxes with a SMILE: Statistical Mode-agnostic Interpretability with Local Explanations
GNN Explainability in a regression setting - semester project for Applied Mathematics MSc @ EPFL
Repository for the paper 'CausalConceptTS: Causal Attributions for Time Series Classification using High Fidelity Diffusion Models'.
Explain model and feature dependencies by decomposition of SHAP values
Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.
Interpretable text embeddings by asking LLMs yes/no questions
For calculating global feature importance using Shapley values.
Influence Estimation for Gradient-Boosted Decision Trees
ES-HyperNEAT Python implementation with C++ computations for NeuroEvolution, Reinforcement Learning and VfMRI
GraphXAI: Resource to support the development and evaluation of GNN explainers
Concise summaries of key papers in responsible AI.
🗺️ Data Cleaning and Textual Data Visualization 🗺️
Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023
Local Universal Rule-based Explanations
[ICML'24] Official PyTorch Implementation of TimeX++
AntakIA is THE tool to explain an ML model or replace it with a collection of basic explainable models.
Post-host prototype-based explanations with rules for time-series classifiers
Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paper "Learning to Receive Help: Intervention-Aware Concept Embedding Models"
Evaluating XAI methods through ablation studies.
Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.
Add a description, image, and links to the explainability topic page so that developers can more easily learn about it.
To associate your repository with the explainability topic, visit your repo's landing page and select "manage topics."