Timezone: »

 
Poster
Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning
Youngkyu Hong · Eunho Yang

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »

Datasets for training machine learning models tend to be biased unless the data is collected with complete care. In such a biased dataset, models are susceptible to making predictions based on the biased features of the data. The biased model fails to generalize to the case where correlations between biases and targets are shifted. To mitigate this, we propose Bias-Contrastive (BiasCon) loss based on the contrastive learning framework, which effectively leverages the knowledge of bias labels. We further suggest Bias-Balanced (BiasBal) regression which trains the classification model toward the data distribution with balanced target-bias correlation. Furthermore, we propose Soft Bias-Contrastive (SoftCon) loss which handles the dataset without bias labels by softening the pair assignment of the BiasCon loss based on the distance in the feature space of the bias-capturing model. Our experiments show that our proposed methods significantly improve previous debiasing methods in various realistic datasets.

Keywords: Machine Learning · Contrastive Learning · Fairness

Author Information

Youngkyu Hong (NAVER AI Lab)
Eunho Yang (Korea Advanced Institute of Science and Technology; AItrics)

More from the Same Authors