Robust Classification under Class-Dependent Domain Shift
Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research. In this paper we explore a special type of dataset shift which we call class-dependent domain shift. It is characterized by the following features: the input data causally depends on the label, the shift in the data is fully explained by a known variable, the variable which controls the shift can depend on the label, there is no shift in the label distribution. We define a simple optimization problem with an information theoretic constraint and attempt to solve it with neural networks. Experiments on a toy dataset demonstrate the proposed method is able to learn robust classifiers which generalize well to unseen domains.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationRobust classificationSimilar Papers 제목 키워드 기반
Regularized Learning for Domain Adaptation under Label Shifts
We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate …
Domain AdaptationA Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification
Many text classification tasks are domain-dependent, and various domain adaptation approaches have been proposed to predict unlabeled data in a new domain. Domain-adversarial neural networks (DANN) and their variants hav…
ClassificationDomain AdaptationGeneral Classificationtext-classification+2Spatial Imputation Drives Cross-Domain Alignment for EEG Classification
Electroencephalogram (EEG) signal classification faces significant challenges due to data distribution shifts caused by heterogeneous electrode configurations, acquisition protocols, and hardware discrepancies across dom…
Representation LearningEgo4OOD: Rethinking Egocentric Video Domain Generalization via Covariate Shift Scoring
Egocentric video action recognition under domain shifts remains challenging due to large intra-class spatio-temporal variability, long-tailed feature distributions, and strong correlations between actions and environment…
Domain GeneralizationBinary ClassificationAction RecognitionSelf-training Avoids Using Spurious Features Under Domain Shift
In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts a…
Domain AdaptationUnsupervised Domain Adaptation