Multi-Objective Few-shot Learning for Fair Classification

Mondal, I., Sen, P. and Ganguly, D. (2021) Multi-Objective Few-shot Learning for Fair Classification. In: 30th ACM International Conference on Information and Knowledge Management (CIKM '21), Queensland, Australia (Virtual Event), 1-5 Nov 2021, pp. 3338-3342. (doi: 10.1145/3459637.3482146)

Abstract

In this paper, we propose a general framework for mitigating the disparities of the predicted classes with respect to secondary attributes within the data (e.g., race, gender etc.). Our proposed method involves learning a multi-objective function that in addition to learning the primary objective of predicting the primary class labels from the data, also employs a clustering-based heuristic to minimize the disparities of the class label distribution with respect to the cluster memberships, with the assumption that each cluster should ideally map to a distinct combination of attribute values. Experiments demonstrate effective mitigation of cognitive biases on a benchmark dataset without the use of annotations of secondary at-tribute values (the zero-shot case) or with the use of a small number of attribute value annotations (the few-shot case).

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Ganguly, Dr Debasis
• Authors: Mondal, I., Sen, P., and Ganguly, D.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Computing Science
• Published Online: 30 October 2021