google-deepmind / distribution_shift_framework
This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).
☆82Updated last month
Related projects: ⓘ
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 4 months ago
- ☆102Updated 11 months ago
- ☆40Updated last year
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆61Updated last year
- Code accompanying paper: Meta-Learning to Improve Pre-Training☆36Updated 2 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆48Updated 3 years ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆39Updated 10 months ago
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆105Updated 2 years ago
- Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments☆73Updated last year
- ☆55Updated 4 years ago
- LISA for ICML 2022☆47Updated last year
- Influence Analysis and Estimation - Survey, Papers, and Taxonomy☆58Updated 6 months ago
- Pytorch library for model calibration metrics and visualizations as well as recalibration methods. In progress!☆65Updated 4 months ago
- The Pitfalls of Simplicity Bias in Neural Networks [NeurIPS 2020] (http://arxiv.org/abs/2006.07710v2)