Continuously Indexed Domain Adaptation

By Hao Wang, Hao He, Dina Katabi. 2020

136 citations recorded by the source corpus.

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one often needs to transfer disease analysis and prediction across patients of different ages, where age acts as a continuous domain index. Such tasks are challenging for prior domain adaptation methods since they ignore the underlying relation among domains. In this paper, we propose the first method for continuously indexed domain adaptation. Our approach combines traditional adversarial adaptation with a novel discriminator that models the encoding-conditioned domain index distribution. Our theoretical analysis demonstrates the value of leveraging the domain index to generate invariant features across a continuous range of domains. Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Peng Gao
2. Xiaogang Wang
3. Tao Qin
4. Ning Xu
5. Qiufeng Wang
6. Shuxia Lin
7. Jindong Wang
8. Kaiwen Zha

Citations in the corpus

• Learngene: From Open-World to Your Learning Task (2021, background): “In addition, neural networks are typically over-parametrized (Han, Mao, and Dally 2016) and easily overfitting few samples (Wang et al. 2020).”
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation (2020, background): “Several other papers (Wulfmeier, Bewley, and Posner 2018; Hoffman et al. 2014; Wang, He, and Katabi 2020; Cheung et al. 2019) presented continuous domain adaptation with the emphasis to generalize on a transitioning target domain.”
• Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, background): “While there are some domain adaptation methods focusing on continuous learning [258], there are only very few investigations on continuous DG [259] whenever this is favorable in real”
• Delving into Deep Imbalanced Regression (2021, background): “Treating different ages as distinct classes is unlikely to yield the best results because it does not take advantage of the similarity between people with nearby ages (Wang et al., 2020).”