Common-Sense Bias Discovery and Mitigation for Classification Tasks

Machine learning model bias can arise from dataset composition: sensitive features correlated to the learning target disturb the model decision rule and lead to performance differences along the features. Existing de-biasing work captures prominent and delicate image features which are traceable in model latent space, like colors of digits or background of animals. However, using the latent space is not sufficient to understand all dataset feature correlations. In this work, we propose a framework to extract feature clusters in a …

bias classification colors cs.cv dataset decision differences digits discovery features image machine machine learning machine learning model model bias performance sense space tasks traceable work