Deep graph regularized learning for binary classification

Minxiang Ye, Vladimir Stankovic, Lina Stankovic, Gene Cheung

Research output: Contribution to conferencePaperpeer-review

7 Citations (Scopus)
73 Downloads (Pure)


With growing interest in data-driven classification, deep learning is now prevalent thanks to its ability to learn feature mapping functions solely from data. For very small training sets, however, deep learning, even with traditional regularization techniques, often overfits, resulting in sub-par classification performance. In this paper, we propose a novel binary classifier deep learning method, based on an iterative quadratic programming (QP) formulation with a graph Laplacian regularizer (GLR), combining the merits of model-based and data-driven approaches. Specifically, the proposed network employs a convolutional neural network (CNN) to learn deep features, which are used to define edge weights for a graph to pose a convex QP problem. Further, we design a novel loss function to penalize samples at the class boundary during semi-supervised learning. Results demonstrate that given a small-size training dataset, our network outperforms several state-of-the-art classifiers, including CNN, model-based GLR, and dynamic graph CNN classifiers.
Original languageEnglish
Number of pages5
Publication statusPublished - 12 May 2019
Event2019 International Conference on Acoustics, Speech, and Signal Processing - Brighton, United Kingdom
Duration: 12 May 201917 May 2019


Conference2019 International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP 2019
Country/TerritoryUnited Kingdom


  • graph Laplacian regularization
  • binary classification
  • semi-supervised learning,
  • deep learning


Dive into the research topics of 'Deep graph regularized learning for binary classification'. Together they form a unique fingerprint.

Cite this