Domain Adaptation as a Problem of Inference on Graphical Models

Abstract

This paper is concerned with data-driven unsupervised domain adaptation, where it is unknown in advance how the joint distribution changes across domains, i.e., what factors or modules of the data distribution remain invariant or change across domains. To develop an automated way of domain adaptation with multiple source domains, we propose to use a graphical model as a compact way to encode the change property of the joint distribution, which can be learned from data, and then view domain adaptation as a problem of Bayesian inference on the graphical models. Such a graphical model distinguishes between constant and varied modules of the distribution and specifies the properties of the changes across domains, which serves as prior knowledge of the changing modules for the purpose of deriving the posterior of the target variable $Y$ in the target domain. This provides an end-to-end framework of domain adaptation, in which additional knowledge about how the joint distribution changes, if available, can be directly incorporated to improve the graphical representation. We discuss how causality-based domain adaptation can be put under this umbrella. Experimental results on both synthetic and real data demonstrate the efficacy of the proposed framework for domain adaptation. The code is available at https://github.com/mgong2/DA_Infer .

19 pages; 8 figures

References in corpus (17)

• Conditional Generative Adversarial Nets
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Learning Transferable Features with Deep Adaptation Networks
• Domain Generalization via Invariant Feature Representation
• Generative Moment Matching Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
• On Causal and Anticausal Learning
• Detecting and Correcting for Label Shift with Black Box Predictors
• Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions
• CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
• Regularized Learning for Domain Adaptation under Label Shifts
• Conditional Generative Moment-Matching Networks
• Causal Generative Neural Networks
• Causal Generative Domain Adaptation Networks
• I-SPEC: An End-to-End Framework for Learning Transportable, Shift-Stable Models

Cited by in corpus (8)

• Evaluating Model Robustness and Stability to Dataset Shift
• A Local Method for Identifying Causal Relations under Markov Equivalence
• Invariant Representation Learning for Treatment Effect Estimation
• AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
• Transferable Time-Series Forecasting under Causal Conditional Shift
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Balance Regularized Neural Network Models for Causal Effect Estimation
• How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?