Fairness in Visual Clustering: A Novel Transformer Clustering Approach
This work addresses fairness issues in visual clustering for reducing demographic bias, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles demographic bias in unsupervised deep clustering by introducing a novel loss function and cross-attention mechanism to improve cluster purity and fairness, achieving enhanced clustering accuracy and fairness on sensitive attributes in large-scale experiments.
Promoting fairness for deep clustering models in unsupervised clustering settings to reduce demographic bias is a challenging goal. This is because of the limitation of large-scale balanced data with well-annotated labels for sensitive or protected attributes. In this paper, we first evaluate demographic bias in deep clustering models from the perspective of cluster purity, which is measured by the ratio of positive samples within a cluster to their correlation degree. This measurement is adopted as an indication of demographic bias. Then, a novel loss function is introduced to encourage a purity consistency for all clusters to maintain the fairness aspect of the learned clustering model. Moreover, we present a novel attention mechanism, Cross-attention, to measure correlations between multiple clusters, strengthening faraway positive samples and improving the purity of clusters during the learning process. Experimental results on a large-scale dataset with numerous attribute settings have demonstrated the effectiveness of the proposed approach on both clustering accuracy and fairness enhancement on several sensitive attributes.