Semi-Supervised Domain Adaptation with Non-Parametric Copulas

2013/01/01 by David López-Paz, David Lopez-Paz, José Miguel Hernández-Lobato +4 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Cancer-related molecular mechanisms research #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Text and Document Classification Technologies #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1301.0142

9 pages, Appearing on Advances in Neural Information Processing Systems 25

arxiv created 2013/01/01 · openalex publication_date 2013/01/01 · arxiv updated 2013/01/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A new framework based on the theory of copulas is proposed to address semi- supervised domain adaptation problems. The presented method factorizes any multivariate density into a product of marginal distributions and bivariate cop- ula functions. Therefore, changes in each of these factors can be detected and corrected to adapt a density model accross different learning domains. Impor- tantly, we introduce a novel vine copula model, which allows for this factorization in a non-parametric manner. Experimental results on regression problems with real-world data illustrate the efficacy of the proposed approach when compared to state-of-the-art techniques.

Citations

• Domain Adaptation: Learning Bounds and Algorithms
• A Survey on Transfer Learning
• A Kernel Method for the Two-Sample Problem

Cited by

• DA-HOC
• A Scalable Room Occupancy Prediction with Transferable Time Series Decomposition of CO 2 Sensor Data

Related

• Unsupervised Domain Adaptation with Copula Models
• Con²DA: Simplifying Semi-supervised Domain Adaptation by Learning Consistent and Contrastive Feature Representations
• Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
• Learning from Label Proportions and Covariate-shifted Instances
• A Primer on Domain Adaptation