Out-of-Distribution Generalization: Challenges and Paper List

Builder & Current Maintainer: Jiashuo Liu(Page)

Credit to THU-TAI Group

Challenges

Paper List

We have summarized the main branches of works for Out-of-Distribution(OOD) Generalization problem, which are classified according to the research focus, including unsupervised representation learning, supervised learning models and optimization methods. For more details, please refer to our survey on OOD generalization(paper).

Branch 1: Unsupervised Representation Learning

1.1 Disentangeled Representation Learning

1.2 Causal Representation Learning

Existing Surveys

Bracnch 2: Supervised Learning Models

2.1 Causal Learning

Invariant Learning

2.2 Domain Generalization

Representation

Training Strategy

Existing Surveys

2.3 Stable Learning

Existing Surveys

Branch 3: Optimization

3.1 Distributionally Robust Optimization

Existing Surveys

3.2 Invariance-Based Optimization

Last updated on April. 21, 2022. (For problems, contact liujiashuo77@gmail.com. To add papers, please pull request at our repo)