Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"
-
Updated
Nov 2, 2021 - Jupyter Notebook
Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"
[ICLR'22] Self-supervised learning optimally robust representations for domain shift.
[NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?
A systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures
"Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data" (NeurIPS 21')
Predicting Out-of-Distribution Error with the Projection Norm
A curated list of Robust Machine Learning papers/articles and recent advancements.
A curated list of Distribution Shift papers/articles and recent advancements.
Course work project for IFT6759 - WILDS - Distribution shifts in wilds - iwildcam
CLIFT : Analysing Natural Distribution Shift on Question Answering Models in Clinical Domain
Coping with Label Shift via Distributionally Robust Optimisation
Robust and Highly Sensitive Covariate Shift Detection using XGBoost
Library for the training and evaluation of object-centric models (ICML 2022)
Implementation of paper: Equivariant Learning for Out-of-Distribution Cold-start Recommendation. (backbone model CLCRec) (MM'23)
Code accompanying the AI4Space 2022 paper "Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications" by Somrita Banerjee, Apoorva Sharma, Edward Schmerling, Max Spolaor, Michael Nemerouf, and Marco Pavone.
Code accompanying our paper titled Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
Domain Adaptation for Time Series Under Feature and Label Shifts
Add a description, image, and links to the distribution-shift topic page so that developers can more easily learn about it.
To associate your repository with the distribution-shift topic, visit your repo's landing page and select "manage topics."