iancovert / removal-explanationsView external linksLinks
A lightweight implementation of removal-based explanations for ML models.
☆59Jul 19, 2021Updated 4 years ago
Alternatives and similar repositories for removal-explanations
Users that are interested in removal-explanations are comparing it to the libraries listed below
Sorting:
- For calculating global feature importance using Shapley values.☆284Updated this week
- For calculating Shapley values via linear regression.☆73Jun 6, 2021Updated 4 years ago
- Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"☆31Apr 28, 2023Updated 2 years ago
- Code for the paper "SMACE: A New Method for the Interpretability of Composite Decision Systems", ECML 2022☆15Apr 17, 2023Updated 2 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆22Oct 13, 2020Updated 5 years ago
- An amortized approach for calculating local Shapley value explanations☆105Nov 29, 2023Updated 2 years ago
- Official Code Repo for the Paper: "How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions", In NeurIPS 2…☆42Oct 31, 2022Updated 3 years ago
- Tools for training explainable models using attribution priors.☆125Mar 19, 2021Updated 4 years ago
- A Python library for working with and training Hidden Markov Models with Poisson emissions.☆10Aug 14, 2017Updated 8 years ago
- CascadER: Cross-Modal Cascading for Knowledge Graph Link Prediction (arXiv 22)☆13Jun 17, 2022Updated 3 years ago
- Pipeline Explorer - Explore and analyze millions of pipelines learned using MLBlocks and MLPrimitives.☆17Jul 6, 2023Updated 2 years ago
- ☆90Oct 7, 2021Updated 4 years ago
- Codebase, data and models for the Headline Grouping paper at NAACL2021☆12Oct 2, 2022Updated 3 years ago
- Tools for robustness evaluation in interpretability methods☆11Jun 25, 2021Updated 4 years ago
- Code for EMNLP 2021 paper "Measuring Association Between Labels and Free-Text Rationales"☆12Sep 12, 2023Updated 2 years ago
- Pretraining summarization models using a corpus of nonsense☆13Sep 28, 2021Updated 4 years ago
- Guiding Attention for Self-Supervised Learning with Transformers☆12Feb 8, 2023Updated 3 years ago
- OCEAN: Optimal Counterfactual Explanations in Tree Ensembles (ICML 2021)☆35Dec 1, 2025Updated 2 months ago
- ☆11Jun 24, 2021Updated 4 years ago
- ☆16Feb 2, 2026Updated last week
- Python package to compute interaction indices that extend the Shapley Value. AISTATS 2023.☆19Sep 25, 2023Updated 2 years ago
- A collection of repeated use utility functions for notebook demos.☆15Nov 2, 2023Updated 2 years ago
- Code repository for the AAAI 2022 paper "Do Feature Attribution Methods Correctly Attribute Features?"☆21Apr 30, 2022Updated 3 years ago
- Learning to Estimate Shapley Values with Vision Transformers☆37Jul 19, 2024Updated last year
- Born-Again Tree Ensembles: Transforms a random forest into a single, minimal-size, tree with exactly the same prediction function in the …☆67Jul 6, 2023Updated 2 years ago
- Local explanations with uncertainty 💐!☆42Aug 8, 2023Updated 2 years ago
- ☆17Jan 29, 2020Updated 6 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆18Apr 25, 2021Updated 4 years ago
- A trio of Google-Colab notebooks (ipynb) for training a GPT-2 (127M) model from scratch (useful for other / non-English languages) using …☆17Jun 29, 2020Updated 5 years ago
- Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)☆43Nov 10, 2022Updated 3 years ago
- XReason - formal reasoning about explanations for ML models☆17May 16, 2025Updated 8 months ago
- Efficient Conformal Prediction via Cascaded Inference with Expanded Admission☆20Sep 15, 2021Updated 4 years ago
- ACL 2021 paper "Style is NOT a single variable: Case Studies for Cross-Style Language Understanding " by Dongyeop Kang and Eduard Hovy☆15Jul 19, 2021Updated 4 years ago
- ☆15Jan 21, 2022Updated 4 years ago
- ☆113Nov 21, 2022Updated 3 years ago
- Principled learning method for Wasserstein distributionally robust optimization with local perturbations (ICML 2020)☆21Mar 24, 2023Updated 2 years ago
- Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders (RecSys 2021)☆20Oct 17, 2021Updated 4 years ago
- Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"☆18Oct 17, 2022Updated 3 years ago
- This is the official implementation for the paper "Learning to Scaffold: Optimizing Model Explanations for Teaching"☆19May 19, 2022Updated 3 years ago