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 13 of 13 for “"equalized odds"”.
-
Luck, Fairness and Bayesian Tensor Completion
… for assessing fairness. Two of these criteria, Equalized Odds and Calibration by Group, have gained significant attention for their simplicity and intuitive appeal, but also for their incompatibility. This chapter provides a perspective on the meaning and consequences of these and other fairness …
-
Contributions to Fairness and Transparency
… for assessing fairness. Two of these criteria, Equalized Odds and Calibration by Group, have gained significant attention for their simplicity and intuitive appeal, but also for their incompatibility. This chapter provides a perspective on the meaning and consequences of these and other fairness …
-
A Study on Comparing AI Models for Fair Social Media Sentiment and Engagement Analysis Across Different COVID-19 Stages
… data from X. Fairness metrics, including average odds difference, equal opportunity difference, equalized odds ratio, disparate impact ratio, and predictive rate parity, were also employed. The results indicated that LSTM combined with sentiment analysis and BERT applied to engagement analysis …
-
Whatls Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias
… metrics, Demographic Parity Difference (DPD) and Equalized Odds Difference (EOD) on models trained with the CelebA, Trifeature, and HateXplain datasets, our results suggest that increasing the distillation temperature improves the distilled student model’s fairness, and the distilled student …
-
Exploring fair machine learning in sequential prediction and supervised learning
… issues of existing fairness notions such as equalized odds. We provide solutions for a simplified version of this problem and insights to deal with further challenges that arise by adopting this notion.
-
Information Bottleneck Methods for Fairness and Privacy in Machine Learning
… work, we consider both demographic parity and equalized odds as fairness constraints, allowing for a more nuanced satisfaction of both criteria. We use the Rényi divergence in developing a loss function involving classical IB measures and show that its parameter α provides an extra degree of …
-
Fairness in Machine Learning Methods for Surgical Skill Assessment
… rate (TPR) and false positive rate (FPR) for equalized odds, to measure bias. These metrics are calculated by comparing rater labels against expert labels within strategically sampled subsets of the data. Our work underscores the necessity of addressing implicit bias in training and test sets …
-
Toxic language and target detection under sparsity by modeling group-specific representations
… result between the Accuracy Parity and Equalized Odds measures, addressing a common misconception that balancing equalized odds across groups automatically leads to balanced accuracy across groups.
-
FAIRNESS IN MACHINE LEARNING AND OPTIMIZATION: APPLICATIONS IN COMPUTATIONAL CRIMINOLOGY
… such as demographic parity, disparate impact, equalized odds, and statistical parity difference can be employed to identify and mitigate inequality. In addition, the dissertation generalizes these concepts to optimization, pre-processing methods such as reweighting methods, and social welfare …
-
Social Fairness in Semi-Supervised Toxicity Text Classification
… models in terms of accuracy and fairness (equalized odds difference) against baselines to clarify the challenges of social fairness in semi-supervised toxicity text classification for the first time. Based on the experimental results, the key contributions of this research are: first, we …
-
Potential Unfairness Associated with the Development of Predictive Risk Models in the New Zealand Child Welfare Context
… accuracy equity, statistical parity, and equalized odds, are also explored. Following the initial evaluation, an in-processing fairness-aware machine learning approach was implemented to address observed biases, focusing specifically on reducing disparities in error rates between Māori …
-
Fairness Without Demographic Attributes in Medical Vision–Language Models
… six protected attributes, Debiased CLIP reduces Equalized Odds Difference on four of six attributes (ethnicity 17.10 to 3.50; language 22.28 to 16.00; age 27.72 to 16.24; marital status 46.88 to 28.57) and improves Equalized Subgroup AUC on five of six, with the largest group-wise gains …
-
TRUSTWORTHY AND EXPLAINABLE MACHINE LEARNING USING INFORMATION-THEORETIC METHODS
… fairness notions, e.g., statistical parity, equalized odds, and predictive parity using the same PID framework, offering a granular understanding of their overlaps and impossibilities. This dissertation lays the foundational principles for data scientists and policymakers toward trustworthy …