Transfer Learning in Heterogeneous Drug-Target Interaction Predictions Using Federated Boosting
Loading...
Date
2023
item.page.title
Transfer Learning in Heterogeneous Drug-Target Interaction Predictions Using Federated Boosting
item.page.contributor
item.page.advisor
Authors
Sándor, Dániel
Antal, Péter
Antal, Péter
item.page.spatial
item.page.createdDate
item.page.extent
item.page.medium
item.page.isbn
item.page.issn
item.page.language
en
Publisher
item.page.replaces
item.page.alternative
item.page.type
könyvfejezet
item.page.accessRights
Open access
item.page.rightsHolder
Szerző
item.page.address
item.page.conferenceDate
2023.02.06-2023.02.07.
item.page.conferencePlace
Budapest
item.page.conferenceTitle
30th Minisymposium of the Department of Measurement and Information Systems
item.page.containerIdentifierIsbn
978-963-421-904-0
item.page.containerIdentifierIssn
item.page.containerPeriodicalNumber
item.page.containerPeriodicalVolume
item.page.containerPeriodicalYear
item.page.containerTitle
Proceedings of the 30th Minisymposium
item.page.contributorLector
item.page.contributor.lector
item.page.contributorBody
item.page.courseCode
item.page.courseName
item.page.dateDefence
item.page.department
Department of Measurement and Information Systems
item.page.descriptionVersion
Post print
item.page.doctoralSchool
item.page.faculty
Faculty of Electrical Engineering and Informatics
item.page.firstpage
41
item.page.identifier
item.page.identifierLectureNotes
item.page.identifierReference
item.page.inscription
item.page.note
item.page.page
item.page.periodicalCreator
item.page.periodicalNumber
item.page.periodicalVolume
item.page.periodicalYear
item.page.scale
item.page.signature
item.page.subjectArea
item.page.subjectField
item.page.subjectOszkar
federated learning
multitask learning
boosting
DTI
multitask learning
boosting
DTI
item.page.technique
item.page.titlenumber
item.page.typeType
Konferenciacikk
item.page.university
Budapest University of Technology and Economics
item.page.universityProgram
item.page.universityProgramLevel
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In multitask federated learning, when small amounts of data are available, it can be harder to achieve proper predictive performance, especially if the clients’ tasks are different. However, task heterogeneity is common in modern Drug-Target interaction (DTI) prediction problems. As the data available for DTI tasks are sparse, it can be challenging for clients to synchronize the tasks used for training. In our method, we used boosting to enhance transfer in the multitask scenario and adapted it to a federated environment, allowing clients to train models without having to agree on the output dimensions. Boosting uses adaptive weighting of the data to train an ensemble of predictors. Weighting data boosting can induce the selection of important tasks when shaping a model’s latent representation. This way boosting contributes to the weighting of tasks on a client level and enhances transfer, while traditional federated algorithms can be used on a global level. We evaluate our results extensively on the tyrosine kinase assays of the KIBA data set to get a clear picture of connections between boosting federated learning and transfer learning.