Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data

Zhengfeng Lai, Chao Wang, Henrry Gunawan, Sen Ching Cheung, Chen Nee Chuah

Research output: Contribution to journalConference articlepeer-review

17 Scopus citations

Abstract

Despite recent promising results on semi-supervised learning (SSL), data imbalance, particularly in the unlabeled dataset, could significantly impact the training performance of a SSL algorithm if there is a mismatch between the expected and actual class distributions. The efforts on how to construct a robust SSL framework that can effectively learn from datasets with unknown distributions remain limited. We first investigate the feasibility of adding weights to the consistency loss and then we verify the necessity of smoothed weighting schemes. Based on this study, we propose a self-adaptive algorithm, named Smoothed Adaptive Weighting (SAW). SAW is designed to enhance the robustness of SSL by estimating the learning difficulty of each class and synthesizing the weights in the consistency loss based on such estimation. We show that SAW can complement recent consistency-based SSL algorithms and improve their reliability on various datasets including three standard datasets and one gigapixel medical imaging application without making any assumptions about the distribution of the unlabeled set.

Original languageEnglish
Pages (from-to)11828-11843
Number of pages16
JournalProceedings of Machine Learning Research
Volume162
StatePublished - 2022
Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States
Duration: Jul 17 2022Jul 23 2022

Bibliographical note

Publisher Copyright:
Copyright © 2022 by the author(s)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data'. Together they form a unique fingerprint.

Cite this