Samuel Dooley
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Samuel Dooley has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hossein Souri
Johns Hopkins University, USA
2 shared publications - Micah Goldblum
Center for Data Science, New York University, New York, NY, USA
2 shared publications - Steven Reich
University of Maryland, USA
2 shared publications - Tom Goldstein
University of Maryland
2 shared publications - Valeriia Cherepanova
University of Maryland, USA
2 shared publications John M. Douglas
Centers for Disease Control and Prevention, Atlanta, Georgia
1 shared publication
Latest Publications
- Open Access
Fairer and More Accurate Tabular Models Through NAS
Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data are ingested, what the model weights are, or how outputs are processed. We employ an emergent and different strategy where we consider updating the model's architecture and training hyperparameters to find an entirely new model with better outcomes from the beginning of the debiasing procedure. In this work, we propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We conduct extensive exploration of architectural and hyperparameter spaces (MLP, ResNet, and FT-Transformer) across diverse datasets, demonstrating the dependence of accuracy and fairness metrics of model predictions on hyperparameter combinations. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We propose a novel approach that jointly optimizes architectural and training hyperparameters in a multi-objective constraint of both accuracy and fairness. We produce architectures that consistently Pareto dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both, all of this while being Pareto-optimal over hyperparameters achieved through single-objective (accuracy) optimization runs. This research underscores the promise of automating fairness and accuracy optimization in deep learning models.
Open AccessFairer and More Accurate Tabular Models Through NAS
Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data are ingested, what the model weights are, or how outputs are processed. We employ an emergent and different strategy where we consider updating the model's architecture and training hyperparameters to find an entirely new model with better outcomes from the beginning of the debiasing procedure. In this work, we propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We conduct extensive exploration of architectural and hyperparameter spaces (MLP, ResNet, and FT-Transformer) across diverse datasets, demonstrating the dependence of accuracy and fairness metrics of model predictions on hyperparameter combinations. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We propose a novel approach that jointly optimizes architectural and training hyperparameters in a multi-objective constraint of both accuracy and fairness. We produce architectures that consistently Pareto dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both, all of this while being Pareto-optimal over hyperparameters achieved through single-objective (accuracy) optimization runs. This research underscores the promise of automating fairness and accuracy optimization in deep learning models.
- Open Access
- 8 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 229-247
A Deep Dive into Dataset Imbalance and Bias in Face Identification
- 8 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 229-247
Open AccessA Deep Dive into Dataset Imbalance and Bias in Face Identification
- Open Access
A Deep Dive into Dataset Imbalance and Bias in Face Identification
As the deployment of automated face recognition (FR) systems proliferates, bias in these systems is not just an academic question, but a matter of public concern. Media portrayals often center imbalance as the main source of bias, i.e., that FR models perform worse on images of non-white people or women because these demographic groups are underrepresented in training data. Recent academic research paints a more nuanced picture of this relationship. However, previous studies of data imbalance in FR have focused exclusively on the face verification setting, while the face identification setting has been largely ignored, despite being deployed in sensitive applications such as law enforcement. This is an unfortunate omission, as 'imbalance' is a more complex matter in identification; imbalance may arise in not only the training data, but also the testing data, and furthermore may affect the proportion of identities belonging to each demographic group or the number of images belonging to each identity. In this work, we address this gap in the research by thoroughly exploring the effects of each kind of imbalance possible in face identification, and discuss other factors which may impact bias in this setting.
Open AccessA Deep Dive into Dataset Imbalance and Bias in Face Identification
As the deployment of automated face recognition (FR) systems proliferates, bias in these systems is not just an academic question, but a matter of public concern. Media portrayals often center imbalance as the main source of bias, i.e., that FR models perform worse on images of non-white people or women because these demographic groups are underrepresented in training data. Recent academic research paints a more nuanced picture of this relationship. However, previous studies of data imbalance in FR have focused exclusively on the face verification setting, while the face identification setting has been largely ignored, despite being deployed in sensitive applications such as law enforcement. This is an unfortunate omission, as 'imbalance' is a more complex matter in identification; imbalance may arise in not only the training data, but also the testing data, and furthermore may affect the proportion of identities belonging to each demographic group or the number of images belonging to each identity. In this work, we address this gap in the research by thoroughly exploring the effects of each kind of imbalance possible in face identification, and discuss other factors which may impact bias in this setting.
- 1 August 2007
- Published by Elsevier in American Journal of Preventive Medicine
- Vol. 33 (2) , S81-S83
Partner Counseling and Referral Services for HIV Infection
- 1 August 2007
- Published by Elsevier in American Journal of Preventive Medicine
- Vol. 33 (2) , S81-S83
Partner Counseling and Referral Services for HIV Infection