Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

Abstract

The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and testing (target) domains is known as domain adaptation. We propose an unsupervised version of domain adaptation that considers the presence of only unlabelled data in the target domain. Our approach centers on finding correspondences between samples of each domain. The correspondences are obtained by treating the source and target samples as graphs and using a convex criterion to match them. The criteria used are first-order and second-order similarities between the graphs as well as a class-based regularization. We have also developed a computationally efficient routine for the convex optimization, thus allowing the proposed method to be used widely. To verify the effectiveness of the proposed method, computer simulations were conducted on synthetic, image classification and sentiment classification datasets. Results validated that the proposed local sample-to-sample matching method out-performs traditional moment-matching methods and is competitive with respect to current local domain-adaptation methods.

arXiv commentFinal version appeared in Engineering Applications of Artificial Intelligence. Mostly, the related work in this version is different from the published version

References in corpus (10)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Frustratingly Easy Domain Adaptation
• Marginalized Denoising Autoencoders for Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Entity Embeddings of Categorical Variables
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Transfer Learning with Joint Adaptation Networks
• Domain Generalization for Object Recognition with Multi-task Autoencoders

Cited by in corpus (15)

• A review of domain adaptation without target labels
• Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
• An introduction to domain adaptation and transfer learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• A Survey on Face Data Augmentation
• Cross-domain Activity Recognition via Substructural Optimal Transport
• Small Sample Learning in Big Data Era
• Virtual Mixup Training for Unsupervised Domain Adaptation
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• Domain Adaptation for Robust Workload Level Alignment Between Sessions and Subjects using fNIRS
• On the unification of the graph edit distance and graph matching problems
• Learning Smooth Representation for Unsupervised Domain Adaptation
• Multi-Prototype Networks for Unconstrained Set-based Face Recognition
• Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
• Low-rank Matrix Recovery With Unknown Correspondence