Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

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

A curated list of trustworthy deep learning papers. Daily updating...

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

Papers about out-of-distribution generalization on graphs.

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

Mechanistically interpretable neurosymbolic AI (Nature Comput Sci 2024): losslessly compressing NNs to computer code and discovering new algorithms which generalize out-of-distribution and outperform human-designed algorithms

The official implementation for ICLR22 paper "Handling Distribution Shifts on Graphs: An Invariance Perspective"

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

Official implementation for the paper "Learning Substructure Invariance for Out-of-Distribution Molecular Representations" (NeurIPS 2022).

Distilling Large Vision-Language Model with Out-of-Distribution Generalizability (ICCV 2023)

[ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization

[NeurIPS 2022] The official repository of Expression Learning with Identity Matching for Facial Expression Recognition

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

A modular and easy-to-use framework for Test-Time Training (TTT) and Test-Time Adaptation (TTA) in Pytorch, making your networks more generalizable with minimal effort ✨

The Pytorch implementation for "Topology-aware Robust Optimization for Out-of-Distribution Generalization" (ICLR 2023)

[NeurIPS 2023] Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Code for ICML21 spotlight paper "Towards open-world recommendation: An inductive model-based collaborative filtering approach"

[NeurIPS 2023] Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Codes and datasets for NeurIPS21 paper “Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach”

The implementation of "Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization" (NeurIPS 2023)

Potential energy ranking for domain generalization (DG)

Code to reproduce the case studies of the 2024 paper "The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology" by Juan L. Gamella, Jonas Peters and Peter Bühlmann.

Velodrome combines semi-supervised learning and out-of-distribution generalization (domain generalization) for drug response prediction and pharmacogenomics

Implementation codes for NeurIPS23 paper "Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts"

The Pytorch implementation for "Are Data-driven Explanations Robust against Out-of-distribution Data?" (CVPR 2023)

Code to reproduce the results from the NSD-synthetic data release paper.

The official repository of our paper "Stretch to Generalize in Molecular Representation Learning with SFL"

This is the official repository for the ICLR 2024 paper Out-Of-Domain Unlabeled Data Improves Generalization.

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models