JonathanCrabbe / Simplex
This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.
β24Updated 2 years ago
Alternatives and similar repositories for Simplex:
Users that are interested in Simplex are comparing it to the libraries listed below
- Local explanations with uncertainty π!β39Updated last year
- Code for "Generative causal explanations of black-box classifiers"β33Updated 4 years ago
- Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)β40Updated 2 years ago
- Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlighβ¦β44Updated last year
- β30Updated 3 years ago
- Self-Explaining Neural Networksβ13Updated last year
- Tensorflow implementation of Invariant Rationalizationβ49Updated 2 years ago
- β44Updated 3 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)β50Updated 3 years ago
- Code for the paper "Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)" (2020)β32Updated 3 years ago
- A benchmark for distribution shift in tabular dataβ50Updated 9 months ago
- An Empirical Framework for Domain Generalization In Clinical Settingsβ30Updated 2 years ago
- β64Updated 4 years ago
- MPVAE: Multivariate Probit Variational AutoEncoder for Multi-Label Classificationβ31Updated 5 months ago
- Codebase for "Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions", ICML 2020.β8Updated 4 years ago
- Neural Additive Models (Google Research)β69Updated 3 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Trainingβ37Updated 3 years ago
- Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.β30Updated 5 years ago
- Code for the ICLR 2022 paper "Attention-based interpretability with Concept Transformers"β40Updated last year
- Code for Estimating Multi-cause Treatment Effects via Single-cause Perturbation (NeurIPS 2021)β12Updated 3 years ago
- Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations (ICML 2022)β27Updated 2 years ago
- Codebase for INVASE: Instance-wise Variable Selection - 2019 ICLRβ60Updated 4 years ago
- Causal Effect Inference for Structured Treatments (SIN) (NeurIPS 2021)β42Updated 2 years ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)β65Updated last year
- Codebase for SEFS: Self-Supervision Enhanced Feature Selection with Correlated Gatesβ23Updated last year
- This is reimplementation of "Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness" in Pytβ¦β48Updated 3 years ago
- Uncertainty Quantification with Pre-trained Language Models: An Empirical Analysisβ14Updated 2 years ago
- β65Updated 7 months ago
- This is the implementation for the NeurIPS 2022 paper: ZIN: When and How to Learn Invariance Without Environment Partition?β22Updated 2 years ago
- Code for "Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties"β18Updated 3 years ago