Causal Generative Domain Adaptation Networks

Abstract

An essential problem in domain adaptation is to understand and make use of distribution changes across domains. For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains. By explicitly modeling the changes, one can even generate data in new domains using the generating process with new values for the latent variables in G-DAN. In practice, the process to generate all features together may involve high-dimensional latent variables, requiring dealing with distributions in high dimensions and making it difficult to learn domain changes from few source domains. Interestingly, by further making use of the causal representation of joint distributions, we then decompose the joint distribution into separate modules, each of which involves different low-dimensional latent variables and can be learned separately, leading to a Causal G-DAN (CG-DAN). This improves both statistical and computational efficiency of the learning procedure. Finally, by matching the feature distribution in the target domain, we can recover the target-domain joint distribution and derive the learning machine for the target domain. We demonstrate the efficacy of both G-DAN and CG-DAN in domain generation and cross-domain prediction on both synthetic and real data experiments.

arXiv comment12 pages

References in corpus (11)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Domain Separation Networks
• Unsupervised Image-to-Image Translation Networks
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Generative Moment Matching Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Joint Distribution Optimal Transportation for Domain Adaptation

Cited by in corpus (10)

• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Few-shot Domain Adaptation by Causal Mechanism Transfer
• Domain Adaptation as a Problem of Inference on Graphical Models
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes
• Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
• Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation
• Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
• Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks
• Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference