Cost-effective Framework for Gradual Domain Adaptation with Multifidelity

02/09/2022
by   Shogo Sagawa, et al.
0

In domain adaptation, when there is a large distance between the source and target domains, the prediction performance will degrade. Gradual domain adaptation is one of the solutions to such an issue, assuming that we have access to intermediate domains, which shift gradually from the source to target domains. In previous works, it was assumed that the number of samples in the intermediate domains is sufficiently large; hence, self-training was possible without the need for labeled data. If access to an intermediate domain is restricted, self-training will fail. Practically, the cost of samples in intermediate domains will vary, and it is natural to consider that the closer an intermediate domain is to the target domain, the higher the cost of obtaining samples from the intermediate domain is. To solve the trade-off between cost and accuracy, we propose a framework that combines multifidelity and active domain adaptation. The effectiveness of the proposed method is evaluated by experiments with both artificial and real-world datasets. Codes are available at https://github.com/ssgw320/gdamf.

READ FULL TEXT

page 3

page 12

research
06/23/2022

Gradual Domain Adaptation via Normalizing Flows

Conventional domain adaptation methods do not work well when a large gap...
research
07/11/2022

Gradual Domain Adaptation without Indexed Intermediate Domains

The effectiveness of unsupervised domain adaptation degrades when there ...
research
06/10/2021

Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent

We focus on the problem of domain adaptation when the goal is shifting t...
research
06/18/2021

Gradual Domain Adaptation via Self-Training of Auxiliary Models

Domain adaptation becomes more challenging with increasing gaps between ...
research
02/10/2023

Federated Domain Adaptation via Gradient Projection

Federated Domain Adaptation (FDA) describes the federated learning setti...
research
05/31/2023

Towards Flow Graph Prediction of Open-Domain Procedural Texts

Machine comprehension of procedural texts is essential for reasoning abo...
research
11/30/2021

TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation

Due to the difficulty of obtaining ground-truth labels, learning from vi...

Please sign up or login with your details

Forgot password? Click here to reset