Multi-Objective Few-shot Learning for Fair Classification
This addresses fairness issues in classification for applications where sensitive attribute data is limited or unavailable.
The paper tackles the problem of mitigating disparities in predicted class distributions with respect to secondary attributes like race or gender, proposing a multi-objective framework that reduces these biases without requiring full attribute annotations, achieving effective mitigation in zero-shot and few-shot scenarios.
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 attribute values (the zero-shot case) or with the use of a small number of attribute value annotations (the few-shot case).