Domain adaptation from multiple sources via auxiliary classifiers

2009 ◽  
Author(s):  
Lixin Duan ◽  
Ivor W. Tsang ◽  
Dong Xu ◽  
Tat-Seng Chua
Keyword(s):  
Domain Adaptation ◽  
Multiple Sources

scholarly journals Multi-Source Distilling Domain Adaptation

2020 ◽  
Vol 34 (07) ◽  
pp. 12975-12983
Author(s):  
Sicheng Zhao ◽  
Guangzhi Wang ◽  
Shanghang Zhang ◽  
Yang Gu ◽  
Yaxian Li ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Feature Space ◽  
Wasserstein Distance ◽  
Training Data ◽  
Source Distribution ◽  
Single Source ◽  
Multiple Sources ◽  
Target Domain ◽  
Target Feature ◽  
Training Samples

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in practice, labeled data may be collected from multiple sources, while naive application of the single-source DA algorithms may lead to suboptimal solutions. In this paper, we propose a novel multi-source distilling domain adaptation (MDDA) network, which not only considers the different distances among multiple sources and the target, but also investigates the different similarities of the source samples to the target ones. Specifically, the proposed MDDA includes four stages: (1) pre-train the source classifiers separately using the training data from each source; (2) adversarially map the target into the feature space of each source respectively by minimizing the empirical Wasserstein distance between source and target; (3) select the source training samples that are closer to the target to fine-tune the source classifiers; and (4) classify each encoded target feature by corresponding source classifier, and aggregate different predictions using respective domain weight, which corresponds to the discrepancy between each source and target. Extensive experiments are conducted on public DA benchmarks, and the results demonstrate that the proposed MDDA significantly outperforms the state-of-the-art approaches. Our source code is released at: https://github.com/daoyuan98/MDDA.

scholarly journals Unsupervised multi-source domain adaptation with no observable source data

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0253415
Author(s):  
Hyunsik Jeon ◽  
Seongmin Lee ◽  
U Kang
Keyword(s):  
Real World ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Multiple Source ◽  
Multiple Sources ◽  
Target Domain ◽  
Source Domain ◽  
Source Data ◽  
Real World Datasets ◽  
Target Data

Given trained models from multiple source domains, how can we predict the labels of unlabeled data in a target domain? Unsupervised multi-source domain adaptation (UMDA) aims for predicting the labels of unlabeled target data by transferring the knowledge of multiple source domains. UMDA is a crucial problem in many real-world scenarios where no labeled target data are available. Previous approaches in UMDA assume that data are observable over all domains. However, source data are not easily accessible due to privacy or confidentiality issues in a lot of practical scenarios, although classifiers learned in source domains are readily available. In this work, we target data-free UMDA where source data are not observable at all, a novel problem that has not been studied before despite being very realistic and crucial. To solve data-free UMDA, we propose DEMS (Data-free Exploitation of Multiple Sources), a novel architecture that adapts target data to source domains without exploiting any source data, and estimates the target labels by exploiting pre-trained source classifiers. Extensive experiments for data-free UMDA on real-world datasets show that DEMS provides the state-of-the-art accuracy which is up to 27.5% point higher than that of the best baseline.

scholarly journals Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

2021 ◽  
Author(s):  
Sicheng Zhao ◽  
Yang Xiao ◽  
Jiang Guo ◽  
Xiangyu Yue ◽  
Jufeng Yang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
Multiple Sources

scholarly journals Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources

2019 ◽  
Vol 33 ◽  
pp. 5989-5996 ◽  
Author(s):  
Yongchun Zhu ◽  
Fuzhen Zhuang ◽  
Deqing Wang
Keyword(s):  
Domain Adaptation ◽  
Feature Space ◽  
Multiple Sources ◽  
Target Domain ◽  
Domain Specific ◽  
Unsupervised Domain Adaptation ◽  
Specific Distribution ◽  
Benchmark Datasets ◽  
Invariant Representations ◽  
Decision Boundaries

While Unsupervised Domain Adaptation (UDA) algorithms, i.e., there are only labeled data from source domains, have been actively studied in recent years, most algorithms and theoretical results focus on Single-source Unsupervised Domain Adaptation (SUDA). However, in the practical scenario, labeled data can be typically collected from multiple diverse sources, and they might be different not only from the target domain but also from each other. Thus, domain adapters from multiple sources should not be modeled in the same way. Recent deep learning based Multi-source Unsupervised Domain Adaptation (MUDA) algorithms focus on extracting common domain-invariant representations for all domains by aligning distribution of all pairs of source and target domains in a common feature space. However, it is often very hard to extract the same domain-invariant representations for all domains in MUDA. In addition, these methods match distributions without considering domain-specific decision boundaries between classes. To solve these problems, we propose a new framework with two alignment stages for MUDA which not only respectively aligns the distributions of each pair of source and target domains in multiple specific feature spaces, but also aligns the outputs of classifiers by utilizing the domainspecific decision boundaries. Extensive experiments demonstrate that our method can achieve remarkable results on popular benchmark datasets for image classification.

scholarly journals MS-DIAL: Multi-Source Domain Alignment Layers for Unsupervised Domain Adaptation

2020 ◽  
Author(s):  
Lucas Fernando Alvarenga e Silva ◽  
Jurandy Almeida
Keyword(s):  
Deep Neural Networks ◽  
Domain Adaptation ◽  
Research Area ◽  
Multiple Sources ◽  
Source Domain ◽  
Unsupervised Domain Adaptation ◽  
Public Datasets ◽  
Alignment Layers ◽  
Domain Alignment ◽  
Different Sources

In general, deep neural networks trained on a given labeled dataset are expected to produce equivalent results when tested on a new unlabeled dataset. However, data are generally collected by different devices or under varying conditions and thus they often are not part of a same domain, yielding poor results. This is due to the domain shift between data distributions and has been the goal of a research area known as unsupervised domain adaptation. Many prior works have been designed to transfer knowledge between two domains: one source to one target. Since data may be taken from different sources and with different distributions, multi-source domain adaptation has received increasing attention. This paper presents the Multi-Source DomaIn Alignment Layers (MS-DIAL), which reduce the domain shift between multiple sources and a given target by embedding domain alignment layers in any given network. Except for the embedded layers, all the other network parameters are shared among all domains, saving processing time and memory usage. Experiments were performed on digit and object recognition tasks with five public datasets widely used to evaluate domain adaptation methods. Results show that the proposed method is promising and outperforms state-of-the-art approaches.

Multiple Graphs and Low-Rank Embedding for Multi-Source Heterogeneous Domain Adaptation

2022 ◽  
Vol 16 (4) ◽  
pp. 1-25
Author(s):  
Hanrui Wu ◽  
Michael K. Ng
Keyword(s):  
Domain Adaptation ◽  
Low Rank ◽  
Multiple Sources ◽  
Target Domain ◽  
Structure Information ◽  
Learning Procedure ◽  
Original Target ◽  
Real World Datasets ◽  
Iterative Optimization Algorithm ◽  
Multiple Domains

Multi-source domain adaptation is a challenging topic in transfer learning, especially when the data of each domain are represented by different kinds of features, i.e., Multi-source Heterogeneous Domain Adaptation (MHDA). It is important to take advantage of the knowledge extracted from multiple sources as well as bridge the heterogeneous spaces for handling the MHDA paradigm. This article proposes a novel method named Multiple Graphs and Low-rank Embedding (MGLE), which models the local structure information of multiple domains using multiple graphs and learns the low-rank embedding of the target domain. Then, MGLE augments the learned embedding with the original target data. Specifically, we introduce the modules of both domain discrepancy and domain relevance into the multiple graphs and low-rank embedding learning procedure. Subsequently, we develop an iterative optimization algorithm to solve the resulting problem. We evaluate the effectiveness of the proposed method on several real-world datasets. Promising results show that the performance of MGLE is better than that of the baseline methods in terms of several metrics, such as AUC, MAE, accuracy, precision, F1 score, and MCC, demonstrating the effectiveness of the proposed method.

scholarly journals Multi-Source Co-adaptation for EEG-Based Emotion Recognition by Mining Correlation Information

2021 ◽  
Vol 15 ◽  
Author(s):  
Jianwen Tao ◽  
Yufang Dan
Keyword(s):  
Emotion Recognition ◽  
Experimental Evidence ◽  
Domain Adaptation ◽  
Multiple Sources ◽  
Individual Subject ◽  
Correlation Information ◽  
Metric Function ◽  
Eeg Features

Since each individual subject may present completely different encephalogram (EEG) patterns with respect to other subjects, existing subject-independent emotion classifiers trained on data sampled from cross-subjects or cross-dataset generally fail to achieve sound accuracy. In this scenario, the domain adaptation technique could be employed to address this problem, which has recently got extensive attention due to its effectiveness on cross-distribution learning. Focusing on cross-subject or cross-dataset automated emotion recognition with EEG features, we propose in this article a robust multi-source co-adaptation framework by mining diverse correlation information (MACI) among domains and features with l2,1−norm as well as correlation metric regularization. Specifically, by minimizing the statistical and semantic distribution differences between source and target domains, multiple subject-invariant classifiers can be learned together in a joint framework, which can make MACI use relevant knowledge from multiple sources by exploiting the developed correlation metric function. Comprehensive experimental evidence on DEAP and SEED datasets verifies the better performance of MACI in EEG-based emotion recognition.

Domain Adaptation for Sentiment Classification in Light of Multiple Sources

2014 ◽  
Vol 26 (3) ◽  
pp. 586-598 ◽  
Author(s):  
Fang Fang ◽  
Kaushik Dutta ◽  
Anindya Datta
Keyword(s):  
Domain Adaptation ◽  
Sentiment Classification ◽  
Multiple Sources
Sign in / Sign up

Export Citation Format

Share Document