Deep Representation Debiasing via Mutual Information Minimization and Maximization (Student Abstract)

Ruijiang Han, Wei Wang, Yuxi Long, Jiajie Peng

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

Deep representation learning has succeeded in several fields. However, pre-trained deep representations are usually biased and make downstream models sensitive to different attributes. In this work, we propose a post-processing unsupervised deep representation debiasing algorithm, DeepMinMax, which can obtain unbiased representations directly from pre-trained representations without re-training or fine-tuning the entire model. The experimental results on synthetic and real-world datasets indicate that DeepMinMax outperforms the existing state-of-the-art algorithms on downstream tasks.

源语言英语
主期刊名IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
出版商Association for the Advancement of Artificial Intelligence
12965-12966
页数2
ISBN(电子版)1577358767, 9781577358763
DOI
出版状态已出版 - 30 6月 2022
活动36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
期限: 22 2月 20221 3月 2022

出版系列

姓名Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
36

会议

会议36th AAAI Conference on Artificial Intelligence, AAAI 2022
Virtual, Online
时期22/02/221/03/22

指纹

探究 'Deep Representation Debiasing via Mutual Information Minimization and Maximization (Student Abstract)' 的科研主题。它们共同构成独一无二的指纹。

引用此