Domain Adaptation under Open Set Label Shift

07/26/2022
by   Saurabh Garg, et al.
0

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS) where the label distribution can change arbitrarily and a new class may arrive during deployment, but the class-conditional distributions p(x|y) are domain-invariant. OSLS subsumes domain adaptation under label shift and Positive-Unlabeled (PU) learning. The learner's goals here are two-fold: (a) estimate the target label distribution, including the novel class; and (b) learn a target classifier. First, we establish necessary and sufficient conditions for identifying these quantities. Second, motivated by advances in label shift and PU learning, we propose practical methods for both tasks that leverage black-box predictors. Unlike typical Open Set Domain Adaptation (OSDA) problems, which tend to be ill-posed and amenable only to heuristics, OSLS offers a well-posed problem amenable to more principled machinery. Experiments across numerous semi-synthetic benchmarks on vision, language, and medical datasets demonstrate that our methods consistently outperform OSDA baselines, achieving 10–25 the proposed methods, establishing finite-sample convergence to the true label marginal and convergence to optimal classifier for linear models in a Gaussian setup. Code is available at https://github.com/acmi-lab/Open-Set-Label-Shift.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/06/2023

RLSbench: Domain Adaptation Under Relaxed Label Shift

Despite the emergence of principled methods for domain adaptation under ...
research
02/12/2018

Detecting and Correcting for Label Shift with Black Box Predictors

Faced with distribution shift between training and test set, we wish to ...
research
03/08/2023

Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment

Multimedia applications are often associated with cross-domain knowledge...
research
05/31/2023

Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms

This paper focuses on supervised and unsupervised online label shift, wh...
research
01/21/2019

Calibration with Bias-Corrected Temperature Scaling Improves Domain Adaptation Under Label Shift in Modern Neural Networks

Label shift refers to the phenomenon where the marginal probability p(y)...
research
05/30/2023

ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models

We study the domain adaptation problem with label shift in this work. Un...
research
11/28/2022

Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations

Spurious correlations, or correlations that change across domains where ...

Please sign up or login with your details

Forgot password? Click here to reset