A repository and benchmark for online test-time adaptation.

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

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

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

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

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

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

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

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

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

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

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

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

Temporally and Distributionally Robust Optimization for Cold-start Recommendation (AAAI'24)

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

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

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