Collection of awesome test-time (domain/batch/instance) adaptation methods

Lightweight, useful implementation of conformal prediction on real data.

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]

Domain Adaptation for Time Series Under Feature and Label Shifts

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

[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.

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

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

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)

Reinforcement Learning Environments for Sustainable Energy Systems

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

A python package providing a benchmark with various specified distribution shift patterns.

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