Loading...
Domain generalization via content factors isolation: a two-level latent variable modeling approach
Gao, Erdun Bondell, Howard Huang, Shaoli Gong, Mingming
Gao, Erdun
Bondell, Howard
Huang, Shaoli
Gong, Mingming
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The purpose of domain generalization is to develop models that exhibit a higher degree of generality, meaning they perform better when evaluated on data coming from previously unseen distributions. Models obtained via traditional methods often cannot distinguish between label-specific and domain-related features in the latent space. To confront this difficulty, we propose formulating a novel data generation process using a latent variable model and postulating a partition of the latent space into content and style parts while allowing for statistical dependency to exist between them. In this model, the distribution of content factors associated with observations belonging to the same class depends on only the label corresponding to that class. In contrast, the distribution of style factors has an additional dependency on the domain variable. We derive constraints that suffice to recover the collection of content factors block-wise and the collection of style factors component-wise while guaranteeing the isolation of content factors. This allows us to produce a stable predictor solely relying on the latent content factors. Building upon these theoretical insights, we propose a practical and efficient algorithm for determining the latent variables under the variational auto-encoder framework. Our simulations with dependent latent variables produce results consistent with our theory, and real-world experiments show that our method outperforms the competitors.
Citation
E. Gao, H. Bondell, S. Huang, and M. Gong, “Domain generalization via content factors isolation: a two-level latent variable modeling approach,” Mach Learn, vol. 114, no. 4, pp. 1–33, Apr. 2025, doi: 10.1007/S10994-024-06717-6/TABLES/5.
Source
Machine Learning
Conference
Keywords
Domain generalization, Generative model, Nonlinear ICA
Subjects
Source
Publisher
Springer Nature