Robust Classification under Class-Dependent Domain Shift
This addresses robustness in machine learning for scenarios with specific, label-dependent distribution shifts, but it is incremental as it builds on existing domain adaptation research with a specialized case.
The paper tackles the problem of class-dependent domain shift, where input data changes between training and test distributions in a label-dependent way, by defining an optimization problem with an information-theoretic constraint and solving it with neural networks. Experiments on a toy dataset show the method learns robust classifiers that generalize well to unseen domains.
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.