When Can Memorization Improve Fairness?
We study to which extent additive fairness metrics (statistical parity, equal opportunity and equalized odds) can be influenced in a multi-class classification problem by memorizing a subset of the population. We give explicit expressions for the bias resulting from memorization in terms of the label and group membership distribution of the memorized dataset and the classifier bias on the unmemorized dataset. We also characterize the memorized datasets that eliminate the bias for all three metrics considered. Finally we provide upper and lower bounds on the total probability mass in the memorized dataset that is necessary for the complete elimination of these biases.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessMemorizationMulti-class ClassificationSimilar Papers 제목 키워드 기반
Quantifying Memorization Across Neural Language Models
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violate…
FairnessMemorizationTrustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond
The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data. Previous theoretical analyses, such as …
AttributeFairnessMemorizationRethinking Federated Unlearning via the Lens of Memorization
Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and rema…
Federated LearningThe Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classification
This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between p…
AttributeFairnessimage-classificationImage Classification+1How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence …
Question Answering