kundajelab / abstention
Algorithms for abstention, calibration and domain adaptation to label shift.
β36Updated 4 years ago
Alternatives and similar repositories for abstention:
Users that are interested in abstention are comparing it to the libraries listed below
- Combating hidden stratification with GEORGEβ63Updated 3 years ago
- Model Patching: Closing the Subgroup Performance Gap with Data Augmentationβ42Updated 4 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" π§ (ICLR 2019)β128Updated 3 years ago
- Reusable BatchBALD implementationβ78Updated last year
- An Empirical Study of Invariant Risk Minimizationβ27Updated 4 years ago
- β64Updated 4 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" htβ¦β127Updated 3 years ago
- Toy datasets to evaluate algorithms for domain generalization and invariance learning.β42Updated 3 years ago
- Label shift experimentsβ16Updated 4 years ago
- β125Updated 3 years ago
- Active and Sample-Efficient Model Evaluationβ24Updated 4 years ago
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotligβ¦β145Updated 2 years ago
- Code/figures in Right for the Right Reasonsβ55Updated 4 years ago
- Code for paper EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEβ38Updated last year
- Simple data balancing baselines for worst-group-accuracy benchmarks.β41Updated last year
- OD-test: A Less Biased Evaluation of Out-of-Distribution (Outlier) Detectors (PyTorch)β62Updated last year
- π€π€ Attentive Mixtures of Experts (AMEs) are neural network models that learn to output both accurate predictions and estimates of featuβ¦β41Updated last year
- Figures & code from the paper "Shortcut Learning in Deep Neural Networks" (Nature Machine Intelligence 2020)β96Updated 2 years ago
- Regularized Learning under label shiftsβ18Updated 5 years ago
- Code for "Generative causal explanations of black-box classifiers"β33Updated 4 years ago
- β62Updated 3 years ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"β160Updated last year
- Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extractionβ35Updated 2 years ago
- Interactive Weak Supervision: Learning Useful Heuristics for Data Labelingβ31Updated 4 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networksβ61Updated 4 years ago
- Tools for training explainable models using attribution priors.β122Updated 3 years ago
- Code accompanying paper: Meta-Learning to Improve Pre-Trainingβ37Updated 3 years ago
- Code for ICML 2018 paper on "Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam" by Khan, Nielsen, Tangkaratt, Lin, β¦β112Updated 6 years ago
- MODALS: Modality-agnostic Automated Data Augmentation in the Latent Spaceβ40Updated 4 years ago
- β51Updated 4 years ago