Login | Register

Tackling Distribution Shift - Detection and Mitigation


Tackling Distribution Shift - Detection and Mitigation

Rafiee Sevyeri, Laya (2022) Tackling Distribution Shift - Detection and Mitigation. PhD thesis, Concordia University.

[thumbnail of Rafiee_PhD_W2023.pdf]
Text (application/pdf)
Rafiee_PhD_W2023.pdf - Accepted Version
Available under License Spectrum Terms of Access.


One of the biggest challenges of employing supervised deep learning approaches is their inability to perform as well beyond standardized datasets in real-world applications. Therefore, abrupt changes in the form of an outlier or overall changes in data distribution after model deployment result in a performance drop. Owing to these changes that induce distributional shifts, we propose two methodologies; the first is the detection of these shifts, and the second is adapting the model to overcome the low predictive performance due to these shifts.
The former usually refers to anomaly detection, the process of finding patterns in the data that do not resemble the expected behavior.
Understanding the behavior of data by capturing their distribution might help us to find those rare and uncommon samples without the need for annotated data. In this thesis, we exploit the ability of generative adversarial networks (GANs) in capturing the latent representation to design a model that differentiates the expected behavior from deviated samples. Furthermore, we integrate self-supervision into generative adversarial networks to improve the predictive performance of our proposed anomaly detection model. In addition, to shift detection, we propose an ensemble approach to adapt a model under varied distributional shifts using domain adaptation.
In summary, this thesis focuses on detecting shifts under the umbrella of anomaly detection as well as mitigating the effect of several distributional shifts by adapting deep learning models using a Bayesian and information theory approach.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (PhD)
Authors:Rafiee Sevyeri, Laya
Institution:Concordia University
Degree Name:Ph. D.
Program:Computer Science
Date:4 December 2022
Thesis Supervisor(s):Fevens, Thomas
Keywords:Distribution Shift, Anomaly Detection, Domain Adaptation
ID Code:991835
Deposited By: Laya Rafiee Sevyeri
Deposited On:21 Jun 2023 14:34
Last Modified:21 Jun 2023 14:34
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top