Zero-shot Domain Adaptation without Domain Semantic Descriptors

Abstract

We propose a method to infer domain-specific models such as classifiers for unseen domains, from which no data are given in the training phase, without domain semantic descriptors. When training and test distributions are different, standard supervised learning methods perform poorly. Zero-shot domain adaptation attempts to alleviate this problem by inferring models that generalize well to unseen domains by using training data in multiple source domains. Existing methods use observed semantic descriptors characterizing domains such as time information to infer the domain-specific models for the unseen domains. However, it cannot always be assumed that such metadata can be used in real-world applications. The proposed method can infer appropriate domain-specific models without any semantic descriptors by introducing the concept of latent domain vectors, which are latent representations for the domains and are used for inferring the models. The latent domain vector for the unseen domain is inferred from the set of the feature vectors in the corresponding domain, which is given in the testing phase. The domain-specific models consist of two components: the first is for extracting a representation of a feature vector to be predicted, and the second is for inferring model parameters given the latent domain vector. The posterior distributions of the latent domain vectors and the domain-specific models are parametrized by neural networks, and are optimized by maximizing the variational lower bound using stochastic gradient descent. The effectiveness of the proposed method was demonstrated through experiments using one regression and two classification tasks.

10 pages, 10 figures

References in corpus (6)

• An Overview of Multi-Task Learning in Deep Neural Networks
• Frustratingly Easy Domain Adaptation
• Domain Generalization via Invariant Feature Representation
• Generalizing Across Domains via Cross-Gradient Training
• Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
• One-Sided Unsupervised Domain Mapping

Cited by in corpus (5)

• Learning Robust Global Representations by Penalizing Local Predictive Power
• Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
• Adversarial Learning for Zero-shot Domain Adaptation
• A Simple Domain Shifting Networkfor Generating Low Quality Images
• Meta-Learning for Koopman Spectral Analysis with Short Time-series