TY - GEN
T1 - Deep Representation Debiasing via Mutual Information Minimization and Maximization (Student Abstract)
AU - Han, Ruijiang
AU - Wang, Wei
AU - Long, Yuxi
AU - Peng, Jiajie
N1 - Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2022/6/30
Y1 - 2022/6/30
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85147604466&partnerID=8YFLogxK
U2 - 10.1609/aaai.v36i11.21619
DO - 10.1609/aaai.v36i11.21619
M3 - 会议稿件
AN - SCOPUS:85147604466
T3 - Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
SP - 12965
EP - 12966
BT - IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
PB - Association for the Advancement of Artificial Intelligence
T2 - 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Y2 - 22 February 2022 through 1 March 2022
ER -