NSF Org: |
IIS Div Of Information & Intelligent Systems |
Recipient: |
|
Initial Amendment Date: | July 22, 2019 |
Latest Amendment Date: | July 22, 2019 |
Award Number: | 1910141 |
Award Instrument: | Standard Grant |
Program Manager: |
Rebecca Hwa
IIS Div Of Information & Intelligent Systems CSE Direct For Computer & Info Scie & Enginr |
Start Date: | August 1, 2019 |
End Date: | July 31, 2022 (Estimated) |
Total Intended Award Amount: | $225,000.00 |
Total Awarded Amount to Date: | $225,000.00 |
Funds Obligated to Date: |
|
History of Investigator: |
|
Recipient Sponsored Research Office: |
3400 N CHARLES ST BALTIMORE MD US 21218-2608 (443)997-1898 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
3400 N Charles St Baltimore MD US 21218-2686 |
Primary Place of Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): | Robust Intelligence |
Primary Program Source: |
|
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.070 |
ABSTRACT
Recent advances in machine learning have enabled a wide range of practical applications including active authentication, autonomous driving, and medical diagnosis. While machine learning algorithms achieve impressive performances for these applications, they have to constantly deal with changing characteristics of input data. Examples of such cases include: recognizing faces under poor lighting conditions and side poses while algorithms are trained on well-illuminated faces at the frontal pose; and detecting and segmenting an organ of interest from low-resolution medical images when available algorithms are instead optimized for high-resolution medical images. This problem is commonly known as domain shift. The accuracies of machine learning systems decrease significantly when domain shifts are present. As a result, users must spend significant amounts of time and money to rebuild machine learning models to work well on new data. This project aims to develop computational methods for automatically detecting the presence of domain shifts, quickly adapting machine learning systems to new data distribution, and intelligently seeking additional information to improve the system's performance. Research outputs of this project, such as software, publications, and best practices will contribute to making a wide range of machine learning systems less vulnerable to perpetual changes of input data, and safer to use in the presence of domain shifts.
To achieve these goals, this project proposes four main thrusts: 1) constructing meta-learning techniques to enable efficient adaptation of classifiers to unseen domains using unlabeled data; 2) developing an optimal reinforcement learning strategy for querying additional information that allows effective generalization when the uncertainty is high; 3) building algorithmic foundations for detecting the presence of domain shifts and preparing machine learning systems for appropriate actions; and 4) validating the proposed approaches with classification and segmentation tasks from large-scale datasets corresponding to autonomous driving and active mobile authentication applications. This project combines recent advances in variational inference, reinforcement learning, and active learning to bring a modern and unique perspective on how to deal with the problem of domain shift.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Machine learning systems face a major challenge when deployed “in the wild”, that is the conditions, or domains, under which the systems were developed differ from those in which we use the systems. This problem is called domain shift or covariate shift. The overall objective of this project was to construct meta-learning algorithms for automatically detecting domain shifts, rapidly adapting machine learning systems to unseen domains, and intelligently query additional information to improve the system’s performance. One of the thrusts addresses an important question of how to generalize to unseen domains rapidly. Our hypothesis is that meta-learning can enable efficient adaptation of a classifier to unseen domains using unlabeled data. To this end, we developed various domain adaptation, federated learning as well as novel neural network architectures for dealing with changing distributions in practical applications. Another thrust addrsses the problem of detecting domain shifts in practical applications. Eight journal and conference papers have been published which describe our findings in this project. Implementation code corresponding to many methods developed in this project have been made publicly available. Furthermore, the PI Ngyuen has written a book called Meta Learning With Medical Imaging and Health Informatics Applications describing many of the methods that were developed in this project.
Last Modified: 04/01/2023
Modified by: Vishal M Patel
Please report errors in award information by writing to: awardsearch@nsf.gov.