scholarly journals Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

2020 ◽  
Vol 34 (05) ◽  
pp. 7830-7838 ◽  
Author(s):  
Han Guo ◽  
Ramakanth Pasunuru ◽  
Mohit Bansal
Keyword(s):  
Loss Function ◽  
Optimal Trajectory ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Data Distribution ◽  
Distance Measures ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Additional Loss

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results. Next, we develop a DistanceNet model which uses these distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task's loss function, so as to achieve better unsupervised domain adaptation. Finally, we extend this model to a novel DistanceNet-Bandit model, which employs a multi-armed bandit controller to dynamically switch between multiple source domains and allow the model to learn an optimal trajectory and mixture of domains for transfer to the low-resource target domain. We conduct experiments on popular sentiment analysis datasets with several diverse domains and show that our DistanceNet model, as well as its dynamic bandit variant, can outperform competitive baselines in the context of unsupervised domain adaptation.

Correlation alignment with attention mechanism for unsupervised domain adaptation

2021 ◽  
pp. 1-7
Author(s):  
Rong Chen ◽  
Chongguang Ren
Keyword(s):  
Natural Language Processing ◽  
Language Processing ◽  
Transfer Process ◽  
Negative Transfer ◽  
Domain Adaptation ◽  
Attention Mechanism ◽  
Target Domain ◽  
Source Domain ◽  
Second Order Statistics ◽  
Unsupervised Domain Adaptation

Domain adaptation aims to solve the problems of lacking labels. Most existing works of domain adaptation mainly focus on aligning the feature distributions between the source and target domain. However, in the field of Natural Language Processing, some of the words in different domains convey different sentiment. Thus not all features of the source domain should be transferred, and it would cause negative transfer when aligning the untransferable features. To address this issue, we propose a Correlation Alignment with Attention mechanism for unsupervised Domain Adaptation (CAADA) model. In the model, an attention mechanism is introduced into the transfer process for domain adaptation, which can capture the positively transferable features in source and target domain. Moreover, the CORrelation ALignment (CORAL) loss is utilized to minimize the domain discrepancy by aligning the second-order statistics of the positively transferable features extracted by the attention mechanism. Extensive experiments on the Amazon review dataset demonstrate the effectiveness of CAADA method.

scholarly journals Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

2021 ◽  
Author(s):  
Jiahao Fan ◽  
Hangyu Zhu ◽  
Xinyu Jiang ◽  
Long Meng ◽  
Cong Fu ◽  
...  
Keyword(s):  
Large Scale ◽  
Domain Adaptation ◽  
Source Model ◽  
Deep Sleep ◽  
Sleep Staging ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Generalization Problem ◽  
Source Models

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

scholarly journals Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

2020 ◽  
Vol 34 (04) ◽  
pp. 6243-6250 ◽  
Author(s):  
Qian Wang ◽  
Toby Breckon
Keyword(s):  
Domain Adaptation ◽  
Feature Space ◽  
Structured Prediction ◽  
Target Domain ◽  
Source Domain ◽  
Domain Specific ◽  
Unsupervised Domain Adaptation ◽  
Deep Feature ◽  
Significant Performance ◽  
Error Accumulation

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains. As a result, classifiers trained from labeled samples in the source domain suffer from significant performance drop when directly applied to the samples from the target domain. To address this issue, different approaches have been proposed to learn domain-invariant features or domain-specific classifiers. In either case, the lack of labeled samples in the target domain can be an issue which is usually overcome by pseudo-labeling. Inaccurate pseudo-labeling, however, could result in catastrophic error accumulation during learning. In this paper, we propose a novel selective pseudo-labeling strategy based on structured prediction. The idea of structured prediction is inspired by the fact that samples in the target domain are well clustered within the deep feature space so that unsupervised clustering analysis can be used to facilitate accurate pseudo-labeling. Experimental results on four datasets (i.e. Office-Caltech, Office31, ImageCLEF-DA and Office-Home) validate our approach outperforms contemporary state-of-the-art methods.

scholarly journals P-Norm Attention Deep CORAL: Extending Correlation Alignment Using Attention and the P-Norm Loss Function

2021 ◽  
Vol 11 (11) ◽  
pp. 5267
Author(s):  
Zhi-Yong Wang ◽  
Dae-Ki Kang
Keyword(s):  
Loss Function ◽  
Domain Adaptation ◽  
Original Data ◽  
Good Representation ◽  
Feature Maps ◽  
Target Domain ◽  
Unsupervised Domain Adaptation ◽  
Adaptation Method ◽  
Deep Coral

CORrelation ALignment (CORAL) is an unsupervised domain adaptation method that uses a linear transformation to align the covariances of source and target domains. Deep CORAL extends CORAL with a nonlinear transformation using a deep neural network and adds CORAL loss as a part of the total loss to align the covariances of source and target domains. However, there are still two problems to be solved in Deep CORAL: features extracted from AlexNet are not always a good representation of the original data, as well as joint training combined with both the classification and CORAL loss may not be efficient enough to align the distribution of the source and target domain. In this paper, we proposed two strategies: attention to improve the quality of feature maps and the p-norm loss function to align the distribution of the source and target features, further reducing the offset caused by the classification loss function. Experiments on the Office-31 dataset indicate that our proposed methodologies improved Deep CORAL in terms of performance.

scholarly journals Theoretic Analysis and Extremely Easy Algorithms for Domain Adaptive Feature Learning

2017 ◽  
Author(s):  
Wenhao Jiang ◽  
Cheng Deng ◽  
Wei Liu ◽  
Feiping Nie ◽  
Fu-lai Chung ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Learning Algorithm ◽  
Feature Learning ◽  
Training Dataset ◽  
Target Domain ◽  
Test Dataset ◽  
Linear Classifiers ◽  
Source Domain ◽  
Effective Learning ◽  
Second Moments

Domain adaptation problems arise in a variety of applications, where a training dataset from the source domain and a test dataset from the target domain typically follow different distributions. The primary difficulty in designing effective learning models to solve such problems lies in how to bridge the gap between the source and target distributions. In this paper, we provide comprehensive analysis of feature learning algorithms used in conjunction with linear classifiers for domain adaptation. Our analysis shows that in order to achieve good adaptation performance, the second moments of the source domain distribution and target domain distribution should be similar. Based on our new analysis, a novel extremely easy feature learning algorithm for domain adaptation is proposed. Furthermore, our algorithm is extended by leveraging multiple layers, leading to another feature learning algorithm. We evaluate the effectiveness of the proposed algorithms in terms of domain adaptation tasks on Amazon review and spam datasets from the ECML/PKDD 2006 discovery challenge.

scholarly journals Unsupervised Domain Adaptation Method Based on Discriminant Sample Selection

2020 ◽  
Vol 38 (4) ◽  
pp. 828-837
Author(s):  
Linlin Wu ◽  
Guohua Peng ◽  
Weidong Yan
Keyword(s):  
Density Estimation ◽  
Classification Accuracy ◽  
Domain Adaptation ◽  
Sample Selection ◽  
Previous Method ◽  
Probability Density Estimation ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Adaptation Method

In order to solve the problem that low classification accuracy caused by the different distribution of training set and test set, an unsupervised domain adaptation method based on discriminant sample selection (DSS) is proposed. DSS projects the samples of different domains onto a same subspace to reduce the distribution discrepancy between the source domain and the target domain, and weights the source domain instances to make the samples more discriminant. Different from the previous method based on the probability density estimation of samples, DSS tries to obtain the sample weights by solving a quadratic programming problem, which avoids the distribution estimation of samples and can be applied to any fields without suffering from the dimensional trouble caused by high-dimensional density estimation. Finally, DSS congregates the same classes by minimizing the intra-class distance. Experimental results show that the proposed method improves the classification accuracy and robustness.

scholarly journals Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

2021 ◽  
Author(s):  
Jiahao Fan ◽  
Hangyu Zhu ◽  
Xinyu Jiang ◽  
Long Meng ◽  
Cong Fu ◽  
...  
Keyword(s):  
Large Scale ◽  
Domain Adaptation ◽  
Source Model ◽  
Deep Sleep ◽  
Sleep Staging ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Generalization Problem ◽  
Source Models

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

scholarly journals Domain Adaptation for Pedestrian Detection Based on Prediction Consistency

2014 ◽  
Vol 2014 ◽  
pp. 1-7
Author(s):  
Yu Li-ping ◽  
Tang Huan-ling ◽  
An Zhi-yong
Keyword(s):  
Computer Vision ◽  
Detection Rate ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Pedestrian Detection ◽  
Experimental Results ◽  
Challenging Problem ◽  
Target Domain ◽  
Source Domain ◽  
Adaptation Model

Pedestrian detection is an active area of research in computer vision. It remains a quite challenging problem in many applications where many factors cause a mismatch between source dataset used to train the pedestrian detector and samples in the target scene. In this paper, we propose a novel domain adaptation model for merging plentiful source domain samples with scared target domain samples to create a scene-specific pedestrian detector that performs as well as rich target domain simples are present. Our approach combines the boosting-based learning algorithm with an entropy-based transferability, which is derived from the prediction consistency with the source classifications, to selectively choose the samples showing positive transferability in source domains to the target domain. Experimental results show that our approach can improve the detection rate, especially with the insufficient labeled data in target scene.

A Study of the Impact of Base Traditional Learners on Transfer Learning Algorithms

2018 ◽  
Vol 27 (06) ◽  
pp. 1850022
Author(s):  
Karl R. Weiss ◽  
Taghi M. Khoshkoftaar
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Domain Adaptation ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Target Domain ◽  
Source Domain ◽  
High Performing ◽  
Machine Learning Methods ◽  
The Impact

A transfer learning environment is characterized by not having sufficient labeled training data from the domain of interest (target domain) to build a high-performing machine learner. Transfer learning algorithms use labeled data from an alternate domain (source domain), that is similar to the target domain, to build high-performing learners. The design of a transfer learning algorithm is typically comprised of a domain adaptation step following by a learning step. The domain adaptation step attempts to align the distribution differences between the source domain and the target domain. Then, the aligned data from the domain adaptation step is used in the learning step, which is typically implemented with a traditional machine learning algorithm. Our research studies the impact of the learning step on the performance of various transfer learning algorithms. In our experiment, we use five unique domain adaptation methods coupled with seven different traditional machine learning methods to create 35 different transfer learning algorithms. We perform comparative performance analyses of the 35 transfer learning algorithms, along with the seven stand-alone traditional machine learning methods. This research will aid machine learning practitioners in the algorithm selection process for a transfer learning environment in the absence of reliable validation techniques.

scholarly journals DC-FUDA: Improving Deep Clustering via Fully Unsupervised Domain Adaptation

2021 ◽  
Author(s):  
Zhimeng Yang ◽  
Zirui Wu ◽  
Ming Zeng ◽  
Yazhou Ren ◽  
Xiaorong Pu ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Adaptive Threshold ◽  
Generation Process ◽  
Target Domain ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Adequate Amount ◽  
Traditional Approaches ◽  
Low Entropy

<div>By transferring knowledge from a source domain, the performance of deep clustering on an unlabeled target domain can be improved. When achieving this, traditional approaches make the assumption that adequate amount of labeled data is available in a source domain. However, this assumption is usually unrealistic in practice. The source domain should be carefully selected to share some characteristics with the target domain, and it can not be guaranteed that rich labeled samples are always available in the selected source domain.</div><div>We propose a novel framework to improve deep clustering by transferring knowledge from a source domain without any labeled data. To select reliable instances in the source domain for transferring, we propose a novel adaptive threshold algorithm to select low entropy instances. To transfer important features of the selected instances, we propose a feature-level domain adaptation network (FeatureDA) which cancels unstable generation process. With extensive experiments, we validate that our method effectively improves deep clustering, without using any labeled data in the source domain. Besides, without using any labeled data in the source domain, our method achieves competitive results, compared to the state-of-the-art methods using labeled data in the source domain.</div>

Sign in / Sign up

Export Citation Format

Share Document