Semi-Supervised Discriminative Classification Robust to Sample-Outliers and Feature-Noises

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Adeli, Ehsan
    • Other Affiliation: Stanford University, Stanford, CA
  • Thung, Kim-Han
    • School of Medicine, Biomedical Research Imaging Center
  • An, Le
    • School of Medicine, Biomedical Research Imaging Center
  • Wu, Guorong
    • School of Medicine, Biomedical Research Imaging Center
  • Shi, Feng
    • Other Affiliation: Biomedical Imaging Research Institute, Cedars Sinai Medical Center, Los Angeles, CA
  • Wang, Tao
    • Other Affiliation: Department of Geriatric Psychiatry, Shanghai Mental Health Center, and the, Alzheimer, s Disease and Related Disorders Center, Shanghai Jiao Tong University, Shanghai, China
  • Shen, Dinggang
    • School of Medicine, Biomedical Research Imaging Center
Abstract
  • Discriminative methods commonly produce models with relatively good generalization abilities. However, this advantage is challenged in real-world applications (e.g., medical image analysis problems), in which there often exist outlier data points (sample-outliers) and noises in the predictor values (feature-noises). Methods robust to both types of these deviations are somewhat overlooked in the literature. We further argue that denoising can be more effective, if we learn the model using all the available labeled and unlabeled samples, as the intrinsic geometry of the sample manifold can be better constructed using more data points. In this paper, we propose a semi-supervised robust discriminative classification method based on the least-squares formulation of linear discriminant analysis to detect sample-outliers and feature-noises simultaneously, using both labeled training and unlabeled testing data. We conduct several experiments on a synthetic, some benchmark semi-supervised learning, and two brain neurodegenerative disease diagnosis datasets (for Parkinson's and Alzheimer's diseases). Specifically for the application of neurodegenerative diseases diagnosis, incorporating robust machine learning methods can be of great benefit, due to the noisy nature of neuroimaging data. Our results show that our method outperforms the baseline and several state-of-the-art methods, in terms of both accuracy and the area under the ROC curve.
Date of publication
Keyword
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
Journal title
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
Journal volume
  • 41
Journal issue
  • 2
Page start
  • 515
Page end
  • 522
Version
  • Postprint
Funder
  • National Institute on Aging
ISSN
  • 1939-3539
  • 0162-8828
Publisher
  • Institute of Electrical and Electronics Engineers (IEEE)

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details nihms954492.pdf 2024-07-26 Public Download