Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 15 of 15 for “"model fairness"”.

  1. Un-fair trojan: Targeted backdoor attacks against model fairness

    <p>Machine learning models have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple …

    njit Repository record for Un-fair trojan: Targeted backdoor attacks against model fairness (opens in a new tab)

  2. Deep learning for dermatology : contributions in model fairness, multi-domain adaptation, and light-weight efficiency

    … to data bias, which manifests as problematic unfairness in their decision-making. In dermatology, this is manifested with variable levels of model accuracy across skin tones (types). Another main problem relates to more recent DNNs that are based on vision transformer (VIT), in which, diverse, …

    ubc Repository record for Deep learning for dermatology : contributions in model fairness, multi-domain adaptation, and light-weight efficiency (opens in a new tab) Download PDF for Deep learning for dermatology : contributions in model fairness, multi-domain adaptation, and light-weight efficiency (opens in a new tab)

  3. Towards Trustworthy and Robust Multi-modal Machine Learning

    … However, as the multi-modal machine learning models evolve, they have faced significant challenges related to biases and unseen data distribution, undermining their trustworthiness and robustness. My research focuses on addressing these challenges through the development of innovative training …

    tamu Repository record for Towards Trustworthy and Robust Multi-modal Machine Learning (opens in a new tab) Embargoed until 2026-12-01

  4. Federated Learning for Early Medical Diagnosis: Enhanced Diabetic Retinopathy Detection in Smart Healthcare

    … sensitive medical data must be centralized for model training, raising concerns about privacy, security, and regulatory compliance. Federated learning offers an alternative by allowing hospitals, clinics, and personal health devices to collaboratively train shared models without exchanging raw …

    kennesaw Repository record for Federated Learning for Early Medical Diagnosis: Enhanced Diabetic Retinopathy Detection in Smart Healthcare (opens in a new tab)

  5. Consequences and Incentives of Fair Learning

    … However, in these domains, considering group fairness as the sole factor often leads to two significant consequences: 1) incentivizing individuals to strategically alter their behavior to obtain desired outcomes (e.g., hiding debt to qualify for a loan), and 2) achieving fairness at the …

    wustl Repository record for Consequences and Incentives of Fair Learning (opens in a new tab)

  6. Exploring Memory-Accuracy Trade-off in Incremental Learning

    … forgetting refers to the tendency of these models to overwrite previously acquired knowledge with new information, leading to a degradation in performance on earlier learned tasks.<br/><br/>To address this issue, considerable efforts have been made, resulting in two main categories of …

    kings Repository record for Exploring Memory-Accuracy Trade-off in Incremental Learning (opens in a new tab) Download PDF for Exploring Memory-Accuracy Trade-off in Incremental Learning (opens in a new tab)

  7. Visual bias mitigation driven by Bayesian uncertainties

    Today, intelligent models are used in applications across all of society, from recidivism prediction, identity verification, a vast collection of healthcare tasks from polyp segmentation to cancer grading, and information retrieval, among many more. The vast majority of these intelligent models are …

    whiterose Download PDF for Visual bias mitigation driven by Bayesian uncertainties (opens in a new tab)

  8. Unfairness Assessment, Explanation and Mitigation in Machine Learning Models for Personalization

    … and evaluation of Artificial Intelligence models that are optimized to operate fairly in the context of voice assistant systems. Assessing the level of performance of existing fairness-aware solutions is an essential step towards comprehending how much effort should be put to provide fair …

    cagliari Repository record for Unfairness Assessment, Explanation and Mitigation in Machine Learning Models for Personalization (opens in a new tab)

  9. Secure Computation and Proportionally Fair Collaboration in Federated Learning of Histopathology Images

    The prediction power of deep learning models depends on the size and quality of the training data. Having access to large-scale datasets enables the model to more precisely estimate the underlying distribution of the data. Deep models rely on training datasets that are ideally aggregated from …

    waterloo Repository record for Secure Computation and Proportionally Fair Collaboration in Federated Learning of Histopathology Images (opens in a new tab)

  10. Trustworthy AI in the Modern Era: Theories and Applications

    … interconnected critical components of modern AI: model security, fairness, explainability, and data privacy. For model security, I aim to ensure that the model integrity and behavior are not compromised against potential malicious attacks, especially model backdoor and stealing attacks. I propose …

    umn Repository record for Trustworthy AI in the Modern Era: Theories and Applications (opens in a new tab)

  11. From minds to machines

    … and multimodal machine learning has produced models capable of synthesizing high-quality text, images, and code. While these systems often exhibit behaviors that resemble human understanding, their impressive surface-level fluency does not reliably indicate the presence of stable, grounded, or …

    lmu-germany Repository record for From minds to machines (opens in a new tab)

  12. Advancing Pandemic Response: Integrated Strategies for Testing, Prediction, and Bias Mitigation

    … strategies, constructing reliable predictive models, and mitigating demographic biases in artificial intelligence (AI) models used for healthcare decision-making. The first study introduces a global screening strategy designed to optimize resource use and increase testing capacity, …

    tenn-hsc Repository record for Advancing Pandemic Response: Integrated Strategies for Testing, Prediction, and Bias Mitigation (opens in a new tab)

  13. Principled and Explainable Reasoning involving Natural Languages

    Reasoning is the process in which statistical models integrate knowledge from multiple sources, internal or external, to generate new information or new knowledge that is deemed reasonable thus providing values to downstream tasks. Needless to say, this very definition lends reasoning to a great …

    penn Repository record for Principled and Explainable Reasoning involving Natural Languages (opens in a new tab) Embargoed until 2027-06-14

  14. Optimization opportunities in human in the loop computational paradigm

    … and learning, to name a few. Finally, fairness and ethical consideration are also of utmost importance in these processes./p><p>This dissertation aims to design solutions for each of the aforementioned stakeholders. The first contribution of this dissertation is the study of …

    njit Repository record for Optimization opportunities in human in the loop computational paradigm (opens in a new tab)

  15. Application of Interpretable Machine Learning Methods to Study the Disease Characteristics and Healthcare Expenditures in Hodgkin’s Lymphoma

    … using interpretable ML methods. 2. Assess the fairness of ML models in predicting health expenditures in HL patients based on their sensitive attributes- sex, race, and economic status. 3. To assess the feasibility of using social media data to study the disease and treatment characteristics of …

    wvu Repository record for Application of Interpretable Machine Learning Methods to Study the Disease Characteristics and Healthcare Expenditures in Hodgkin’s Lymphoma (opens in a new tab)