Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Data-Driven Approach to Multiple-Source Domain Adaptation.

ABSTRACT: A key problem in domain adaptation is determining what to transfer across different domains. We propose a data-driven method to represent these changes across multiple source domains and perform unsupervised domain adaptation. We assume that the joint distributions follow a specific generating process and have a small number of identifiable changing parameters, and develop a data-driven method to identify the changing parameters by learning low-dimensional representations of the changing class-conditional distributions across multiple source domains. The learned low-dimensional representations enable us to reconstruct the target-domain joint distribution from unlabeled target-domain data, and further enable predicting the labels in the target domain. We demonstrate the efficacy of this method by conducting experiments on synthetic and real datasets.

SUBMITTER: Stojanov P

PROVIDER: S-EPMC6730632 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Data-Driven Approach to Multiple-Source Domain Adaptation.

Stojanov Petar P Gong Mingming M Carbonell Jaime G JG Zhang Kun K

Proceedings of machine learning research 20190401

A key problem in domain adaptation is determining what to transfer across different domains. We propose a data-driven method to represent these changes across multiple source domains and perform unsupervised domain adaptation. We assume that the joint distributions follow a specific generating process and have a small number of identifiable changing parameters, and develop a data-driven method to identify the changing parameters by learning low-dimensional representations of the changing class-c ...[more]

PMID: 31497777

Similar Datasets

Unsupervised multi-source domain adaptation with no observable source data.

Project description: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.

| S-EPMC8270218 | biostudies-literature

A Data-Driven Latent Variable Approach to Validating the Research Domain Criteria Framework.

Project description:Despite the widespread use of the Research Domain Criteria (RDoC) framework in psychiatry and neuroscience, recent studies suggest that the RDoC is insufficiently specific or excessively broad relative to the underlying brain circuitry it seeks to elucidate. To address these concerns of the RDoC framework, our study employed a latent variable approach, specifically utilizing bifactor analysis. We examined a total of 84 whole-brain task-based fMRI (tfMRI) activation maps from 19 studies with a total of 6,192 participants. Within this set of 84 maps, a curated subset of 37 maps with a balanced representation of RDoC domains constituted the training set of our analysis, and the remaining held-out maps formed the internal validation set. External validation was performed with 36 peak coordinate activation maps from Neurosynth, using terms of RDoC constructs as seeds for topic meta-analysis. Our results indicate that a bifactor model with a task-general domain and splitting the cognitive systems domain into sub-domains better fits the current corpus of tfMRI data than the current RDoC framework. Our data-driven validation supports revising the RDoC framework to accurately reflect underlying brain circuitry.

| S-EPMC10979851 | biostudies-literature

Adversarial domain adaptation for cross data source macromolecule in situ structural classification in cellular electron cryo-tomograms.

Project description:MotivationSince 2017, an increasing amount of attention has been paid to the supervised deep learning-based macromolecule in situ structural classification (i.e. subtomogram classification) in cellular electron cryo-tomography (CECT) due to the substantially higher scalability of deep learning. However, the success of such supervised approach relies heavily on the availability of large amounts of labeled training data. For CECT, creating valid training data from the same data source as prediction data is usually laborious and computationally intensive. It would be beneficial to have training data from a separate data source where the annotation is readily available or can be performed in a high-throughput fashion. However, the cross data source prediction is often biased due to the different image intensity distributions (a.k.a. domain shift).ResultsWe adapt a deep learning-based adversarial domain adaptation (3D-ADA) method to timely address the domain shift problem in CECT data analysis. 3D-ADA first uses a source domain feature extractor to extract discriminative features from the training data as the input to a classifier. Then it adversarially trains a target domain feature extractor to reduce the distribution differences of the extracted features between training and prediction data. As a result, the same classifier can be directly applied to the prediction data. We tested 3D-ADA on both experimental and realistically simulated subtomogram datasets under different imaging conditions. 3D-ADA stably improved the cross data source prediction, as well as outperformed two popular domain adaptation methods. Furthermore, we demonstrate that 3D-ADA can improve cross data source recovery of novel macromolecular structures.Availability and implementationhttps://github.com/xulabs/projects.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC6612867 | biostudies-literature

wenda_gpu: fast domain adaptation for genomic data.

Project description:MotivationDomain adaptation allows for the development of predictive models even in cases with limited sample data. Weighted elastic net domain adaptation specifically leverages features of genomic data to maximize transferability but the method is too computationally demanding to apply to many genome-sized datasets.ResultsWe developed wenda_gpu, which uses GPyTorch to train models on genomic data within hours on a single GPU-enabled machine. We show that wenda_gpu returns comparable results to the original wenda implementation, and that it can be used for improved prediction of cancer mutation status on small sample sizes than regular elastic net.Availability and implementationwenda_gpu is available on GitHub at https://github.com/greenelab/wenda_gpu/.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC9665854 | biostudies-literature

Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation.

Project description:Probability discrepancy measure is a fundamental construct for numerous machine learning models such as weakly supervised learning and generative modeling. However, most measures overlook the fact that the distributions are not the end-product of learning, but are the input of a downstream predictor. Therefore, it is important to warp the probability discrepancy measure towards the end tasks, and towards this goal, we propose a new bi-level optimization based approach so that the two distributions are compared not uniformly against the entire hypothesis space, but only with respect to the optimal predictor for the downstream end task. When applied to margin disparity discrepancy and contrastive domain discrepancy, our method significantly improves the performance in unsupervised domain adaptation, and enjoys a much more principled training process.

| S-EPMC9358785 | biostudies-literature

Implementation of a data repository-driven approach for targeted proteomics experiments by multiple reaction monitoring.

Project description:Multiple reaction monitoring (MRM), commonly employed for the mass spectrometric detection of small molecules, is rapidly gaining ground in proteomics. Its high sensitivity and specificity makes this targeted approach particularly useful when sample throughput or proteome coverage limits global studies. Existing tools to design MRM assays rely exclusively on theoretical predictions, or combine them with previous observations on the same type of sample. The additional mass spectrometric experimentation this requires can pose significant demands on time and material. To overcome these challenges, a new MRM worksheet was introduced into The Global Proteome Machine database (GPMDB) that provided all of the information needed to design MRM transitions based solely on archived observations made by other researchers in previous experiments. This required replacing the precursor ion intensity by the number of peptide observations, which proved to be an adequate substitute if peptides did not occur in multiple forms. While the absence of collision energy information proved largely inconsequential, successful prediction of unique transitions depended on the type of fragment ion involved. The design of MRM assays for iTRAQ-labeled tryptic peptides obtained from human platelet proteins demonstrated the usefulness of the MRM worksheet also for quantitative applications. This workflow, which relies exclusively on experimental observations stored in data repositories, therefore represents an attractive alternative for the prediction of MRM transitions prior to experimental validation and optimization.

| S-EPMC2706936 | biostudies-literature

CALDA: Improving Multi-Source Time Series Domain Adaptation With Contrastive Adversarial Learning.

Project description:Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. In cases where meta-domain information such as label distributions is available, weak supervision can further boost performance. We propose a novel framework, CALDA, to tackle these two problems. CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data. Similar to prior methods, CALDA utilizes adversarial learning to align source and target feature representations. Unlike prior approaches, CALDA additionally leverages cross-source label information across domains. CALDA pulls examples with the same label close to each other, while pushing apart examples with different labels, reshaping the space through contrastive learning. Unlike prior contrastive adaptation methods, CALDA requires neither data augmentation nor pseudo labeling, which may be more challenging for time series. We empirically validate our proposed approach. Based on results from human activity recognition, electromyography, and synthetic datasets, we find utilizing cross-source information improves performance over prior time series and contrastive methods. Weak supervision further improves performance, even in the presence of noise, allowing CALDA to offer generalizable strategies for MS-UDA.

| S-EPMC10805953 | biostudies-literature

Unsupervised Domain Adaptation With Optimal Transport in Multi-Site Segmentation of Multiple Sclerosis Lesions From MRI Data.

Project description:Automatic segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) images is essential for clinical assessment and treatment planning of MS. Recent years have seen an increasing use of Convolutional Neural Networks (CNNs) for this task. Although these methods provide accurate segmentation, their applicability in clinical settings remains limited due to a reproducibility issue across different image domains. MS images can have highly variable characteristics across patients, MRI scanners and imaging protocols; retraining a supervised model with data from each new domain is not a feasible solution because it requires manual annotation from expert radiologists. In this work, we explore an unsupervised solution to the problem of domain shift. We present a framework, Seg-JDOT, which adapts a deep model so that samples from a source domain and samples from a target domain sharing similar representations will be similarly segmented. We evaluated the framework on a multi-site dataset, MICCAI 2016, and showed that the adaptation toward a target site can bring remarkable improvements in a model performance over standard training.

| S-EPMC7075308 | biostudies-literature

DomainATM: Domain adaptation toolbox for medical data analysis.

Project description:Domain adaptation (DA) is an important technique for modern machine learning-based medical data analysis, which aims at reducing distribution differences between different medical datasets. A proper domain adaptation method can significantly enhance the statistical power by pooling data acquired from multiple sites/centers. To this end, we have developed the Domain Adaptation Toolbox for Medical data analysis (DomainATM) - an open-source software package designed for fast facilitation and easy customization of domain adaptation methods for medical data analysis. The DomainATM is implemented in MATLAB with a user-friendly graphical interface, and it consists of a collection of popular data adaptation algorithms that have been extensively applied to medical image analysis and computer vision. With DomainATM, researchers are able to facilitate fast feature-level and image-level adaptation, visualization and performance evaluation of different adaptation methods for medical data analysis. More importantly, the DomainATM enables the users to develop and test their own adaptation methods through scripting, greatly enhancing its utility and extensibility. An overview characteristic and usage of DomainATM is presented and illustrated with three example experiments, demonstrating its effectiveness, simplicity, and flexibility. The software, source code, and manual are available online.

| S-EPMC9908850 | biostudies-literature

A data-driven approach to violin making.

Project description:Of all the characteristics of a violin, those that concern its shape are probably the most important ones, as the violin maker has complete control over them. Contemporary violin making, however, is still based more on tradition than understanding, and a definitive scientific study of the specific relations that exist between shape and vibrational properties is yet to come and sorely missed. In this article, using standard statistical learning tools, we show that the modal frequencies of violin tops can, in fact, be predicted from geometric parameters, and that artificial intelligence can be successfully applied to traditional violin making. We also study how modal frequencies vary with the thicknesses of the plate (a process often referred to as plate tuning) and discuss the complexity of this dependency. Finally, we propose a predictive tool for plate tuning, which takes into account material and geometric parameters.

| S-EPMC8096844 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data