Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
Domain adaptation algorithms are useful when the distributions of the training and the test data are different. In this paper, we focus on the problem of instrumental variation and time-varying drift in the field of sensors and measurement, which can be viewed as discrete and continuous distributional change in the feature space. We propose maximum independence domain adaptation (MIDA) and semi-supervised MIDA (SMIDA) to address this problem. Domain features are first defined to describe the background information of a sample, such as the device label and acquisition time. Then, MIDA learns a subspace which has maximum independence with the domain features, so as to reduce the inter-domain discrepancy in distributions. A feature augmentation strategy is also designed to project samples according to their backgrounds so as to improve the adaptation. The proposed algorithms are flexible and fast. Their effectiveness is verified by experiments on synthetic datasets and four real-world ones on sensors, measurement, and computer vision. They can greatly enhance the practicability of sensor systems, as well as extend the application scope of existing domain adaptation algorithms by uniformly handling different kinds of distributional change.
Code (2)
Tasks
Domain AdaptationSimilar Papers 제목 키워드 기반
Content-Style Identification via Differential Independence
Generative analysis often models multi-domain observations as nonlinear mixtures of domain-invariant content variables and domain-specific style variables. Identifying both factors from unpaired domains enables tasks suc…
Image GenerationDIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation
Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data. However, generalizing across heterogeneous domains remains a major challenge due to severe distribution shifts. Existing methods primarily …
Graph Neural NetworkDomain AdaptationTarget Conditioned Representation Independence (TCRI); From Domain-Invariant to Domain-General Representations
We propose a Target Conditioned Representation Independence (TCRI) objective for domain generalization. TCRI addresses the limitations of existing domain generalization methods due to incomplete constraints. Specifically…
Domain GeneralizationInvariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
Domain generalization asks for models trained over a set of training environments to generalize well in unseen test environments. Recently, a series of algorithms such as Invariant Risk Minimization (IRM) have been propo…
Binary ClassificationDomain GeneralizationMulti-class ClassificationregressionProvable Domain Generalization via Invariant-Feature Subspace Recovery
Domain generalization asks for models trained over a set of training environments to perform well in unseen test environments. Recently, a series of algorithms such as Invariant Risk Minimization (IRM) has been proposed …
Domain Generalization