LVR

2000년 도입 · 논문 4편에서 사용

Method introduces a novel unlabeled debiasing technique which works on classification task to reduce the bias of the transformer based language models on downstream classification task. In their method authors use the classes as metric for regularization and punish the network if the embedding produced by the model are far from each other. by doing so the authors claim to be able to reduce the domain shift caused by any unwanted attribute information hence results in fair embedding.

출처: Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization

소개 논문: Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization