Popular GitHub Repositories for Distribution Shift

Lightweight, useful implementation of conformal prediction on real data.

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

[NeurIPS 2022] Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs

Library for the training and evaluation of object-centric models (ICML 2022)

[ICLR'23] Implementation of "Empowering Graph Representation Learning with Test-Time Graph Transformation"

"Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data" (NeurIPS 21')

Official PyTorch implementation of the ICCV'23 paper “Anomaly Detection under Distribution Shift”

The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.

A curated list of papers and resources about the distribution shift in machine learning.

Official repository for the ICLR 2023 paper "A Learning Based Hypothesis Test for Harmful Covariate Shift"

Global-Local Regularization Via Distributional Robustness (AISTATS 2023)

Code for "LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shifts"

Code for the control+shift paper, where a method for generating general datasets with a controllable amount of distribution shift was proposed. Presented at the ECCV'24 "Synthetic Data for Computer Vision" workshop.