A repository and benchmark for online test-time adaptation.

Frouros: an open-source Python library for drift detection in machine learning systems.

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

The official API of DoubleAdapt (KDD'23), an incremental learning framework for online stock trend forecasting, WITHOUT dependencies on the qlib package.

A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).

This repository contains the code of the distribution shift framework presented in A Fine-Grained Analysis on Distribution Shift (Wiles et al., 2022).

The official implementation for ICLR23 paper "GNNSafe: Energy-based Out-of-Distribution Detection for Graph Neural Networks"

"Towards Semi-supervised Learning with Non-random Missing Labels" by Yue Duan (ICCV 2023)

[NeurIPS] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?

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”

Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift

[ICLR 2023] Official Tensorflow implementation of "Distributionally Robust Post-hoc Classifiers under Prior Shifts"

📦 A Python package for online changepoint detection, implementing state-of-the-art algorithms and a novel approach based on neural networks.

[ICLR'22] Self-supervised learning optimally robust representations for domain shift.

NeurIPS22 "RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection" and T-PAMI Extension