From Discrete to Continuous: Deep Fair Clustering With Transferable Representations

arXiv:2403.16201v1 Announce Type: new
Abstract: We consider the problem of deep fair clustering, which partitions data into clusters via the representations extracted by deep neural networks while hiding sensitive data attributes. To achieve fairness, existing methods present a variety of fairness-related objective functions based on the group fairness criterion. However, these works typically assume that the sensitive attributes are discrete and do not work for continuous sensitive variables, such as the proportion of the female population in an area. Besides, …

abstract arxiv clustering continuous criterion cs.cv cs.cy cs.lg data fair fairness functions however networks neural networks type via