Robust deep graph based learning for binary classification

Ye, Minxiang and Stankovic, Vladimir and Stankovic, Lina and Cheung, Gene (2020) Robust deep graph based learning for binary classification. IEEE Transactions on Signal and Information Processing over Networks, 7. pp. 322-335. ISSN 2373-7778 (https://doi.org/10.1109/TSIPN.2020.3040993)

[thumbnail of Ye-etal-IEEE-TSIPN-2020-Robust-deep-graph-based-learning-for-binary]
Preview
 Text. Filename: Ye_etal_IEEE_TSIPN_2020_Robust_deep_graph_based_learning_for_binary.pdf
Accepted Author Manuscript
Download (2MB)| Preview

Abstract

Convolutional neural network (CNN)-based feature learning has become the state-of-the-art for many applications since, given sufficient training data, CNN can significantly outperform traditional methods for various classification tasks. However, feature learning is more challenging if training labels are noisy as CNN tends to overfit to the noisy training labels, resulting in sub-par classification performance. In this paper, we propose a robust binary classifier by learning CNN-based deep metric functions, to construct a graph, used to clean the noisy labels via graph Laplacian regularization (GLR). The denoised labels are then used in two proposed loss correction functions to regularize the deep metric functions. As a result, the node-to-node correlations in the graph are better reflected, leading to improved predictive performance. The experiments on three datasets, varying in number and type of features and under different levels of noise, demonstrate that given a noisy training dataset for the semi-supervised classification task, our proposed networks outperform several state-of-the-art classifiers, including label-noise robust support vector machine, CNNs with three different robust loss functions, model-based GLR, and dynamic graph CNN classifiers.

  • Item type:Article
    ID code:74627
    Dates:
    Date
    Event
    27 November 2020
    Published
    12 November 2020
    Accepted
    Notes:© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Electronic and Electrical Engineering
    Depositing user: Pure Administrator
    Date deposited:17 Nov 2020 12:00
    Last modified:16 Apr 2024 00:29
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/74627
CORE (COnnecting REpositories)