DS Ph.D. Qualifier Presentation | Nicholas Josselyn | Thurs. Dec. 7th @ 12:00pm EST

Thursday, December 7, 2023
12:00 p.m. to 1:00 p.m.
Floor/Room #
303 Conference Room

DATA SCIENCE 

Ph.D. Qualifier Presentation

Nicholas Josselyn

 Thursday, December 7th , 2023 | 12:00 PM EST

Location: Gordon Library 303 Conference Room 

  

Committee: 

Prof. Elke Rundensteiner, research advisor 

Prof. Ziming Zhang, research advisor 

Prof. Randy Paffenroth, Qual co-advisor 

Prof. Reza Zekavat, Qual co-advisor 

 

Title:  

Ensembles of Statistically Independent Models: An Embarrassingly Simple yet Strong Method for Domain Adaptation

Abstract: 

Over recent years many sophisticated methods for the critical problem of domain adaptation (DA) have been proposed in literature. Unfortunately, there is no single DA model that always outperforms others regardless of datasets and setups. Motivated by this, we propose to investigate the effect of ensembles of (imperfect) classic DA models each pre-trained on distinct folds of data on the ability to learn a simple yet strong DA model for solving a particular new target problem. We find that a simple fusion of approximately statistically independent models can significantly boost the performance over each individual DA model. We demonstrate that, when taken together, the rich variety of these ensembled models succeeds to better cover the feature space for domain adaptation, achieving state-of-the-art performance on benchmark data sets for both single-source adaptation like DomainNet (+3.5%) and multi-source adaptation for Office-31 and DomainNet (+3.1% and +5.9%, respectively).   

Research was sponsored by DEVCOM Army Research Laboratory under Cooperative Agreement W911NF-19-2-0112, W911NF-17-2-0227, W911NF1920108, and partially supported by DOE GANN P200A180088 Fellowship and NSF grants 1815866, 1910880, CCF-2006738, NRT-CEDAR 2021871.  

Audience(s)

Department(s):

Data Science
Contact Person
Kelsey Briggs

Phone Number: