Affinity Clustering Framework for Data Debiasing Using Pairwise Distribution Discrepancy

원문 초록

Group imbalance, resulting from inadequate or unrepresentative data collection methods, is a primary cause of representation bias in datasets. Representation bias can exist with respect to different groups of one or more protected attributes and might lead to prejudicial and discriminatory outcomes toward certain groups of individuals; in cases where a learning model is trained on such biased data. This paper presents MASC, a data augmentation approach that leverages affinity clustering to balance the representation of non-protected and protected groups of a target dataset by utilizing instances of the same protected attributes from similar datasets that are categorized in the same cluster as the target dataset by sharing instances of the protected attribute. The proposed method involves constructing an affinity matrix by quantifying distribution discrepancies between dataset pairs and transforming them into a symmetric pairwise similarity matrix. A non-parametric spectral clustering is then applied to this affinity matrix, automatically categorizing the datasets into an optimal number of clusters. We perform a step-by-step experiment as a demo of our method to show the procedure of the proposed data augmentation method and evaluate and discuss its performance. A comparison with other data augmentation methods, both pre- and post-augmentation, is conducted, along with a model evaluation analysis of each method. Our method can handle non-binary protected attributes so, in our experiments, bias is measured in a non-binary protected attribute setup w.r.t. racial groups distribution for two separate minority groups in comparison with the majority group before and after debiasing. Empirical results imply that our method of augmenting dataset biases using real (genuine) data from similar contexts can effectively debias the target datasets comparably to existing data augmentation strategies.