02/02/2021

Hypothesis Disparity Regularized Mutual Information Maximization

Qicheng Lao, Xiang Jiang, Mohammad Havaei

Keywords:

Abstract Paper Similar Papers

Abstract: We propose a hypothesis disparity regularized mutual information maximization (HDMI) approach to tackle unsupervised hypothesis transfer---as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation (UDA)---where the knowledge from a source domain is transferred solely through hypotheses and adapted to the target domain in an unsupervised manner. In contrast to the prevalent HTL and UDA approaches that typically use a single hypothesis, HDMI employs multiple hypotheses to leverage the underlying distributions of the source and target hypotheses. To better utilize the crucial relationship among different hypotheses---as opposed to unconstrained optimization of each hypothesis independently---while adapting to the unlabeled target domain through mutual information maximization, HDMI incorporates a hypothesis disparity regularization that coordinates the target hypotheses jointly learn better target representations while preserving more transferable source knowledge with better-calibrated prediction uncertainty. HDMI achieves state-of-the-art adaptation performance on benchmark datasets for UDA in the context of HTL, without the need to access the source data during the adaptation.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948375
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 4:37 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 9:59 
 0
 0
 0
 1
 3:09 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 0:58 
 0
 0
 0
 0
 6:24 
 0
 0
 0
 1
 14:11 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 7:01 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 1
 5:14 
 0
 0
 0
 0
 12:51 
 0
 0
 0
 0
 8:03 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 9:22 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 13:20 
 0
 0
 0
 0
 14:14 
 0
 0
 0
 0
 9:19 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 15:31 
 1
 1
 0
 0
 1:01 
 0
 0
 0
 0
 15:19 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 1:03 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 11:28 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 13:52 
 0
 0
 0
 0
 13:09