Out-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc

Lightweight, useful implementation of conformal prediction on real data.

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

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

A repository and benchmark for online test-time adaptation.

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.

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).

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

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

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

[NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?

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

[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')