SGDOL: Self-evolving Generative and Discriminative Online Learning for Data Stream Classification

SGDOL: Self-evolving Generative and Discriminative Online Learning for Data Stream Classification

2021 International Conference on Data Mining Workshops (ICDMW)

10.1109/ICDMW53433.2021.00047

http://dx.doi.org/10.1109/icdmw53433.2021.00047

Deeksha Aggarwal, J. Senthilnath, Uttam Kumar, Vivek Yadav, Sushant Kulkarni, Md Meftahul Ferdaus, Li Xiaoli

20 January 2022

Aggarwal, D., Senthilnath, J., Kumar, U., Yadav, V., Kulkarni, S., Ferdaus, M. M., & Xiaoli, L. (2021). SGDOL: Self-evolving Generative and Discriminative Online Learning for Data Stream Classification. 2021 International Conference on Data Mining Workshops (ICDMW). doi:10.1109/icdmw53433.2021.00047

Data streams are usually non-stationary obtained from the same or different data sources. It needs to be processed sequentially, hence termed stream processing. Stream processing often demands evolving neural network architectures that can alter the number of nodes and layers on-demand to classify data streams in an online manner, known as evolving online learning. Traditional deep neural networks (DNNs) uses batch data processing, often limited by their static network structures and offline learning approaches while addressing data streams. In this work, we propose a novel evolving deep neural network framework, known as Self-evolving Generative and Discriminative Online Learning (SGDOL), which utilises an online learning approach to evolve both generator and discriminator network structure from scratch, and on-demand to classify data streams. The dynamic feature learning mechanism of autoencoder-based generative models have demonstrated its potential in learning latent feature representations from data streams. These latent features are fed to the evolving feed-forward DNN-based discriminator as input. The mechanism of adding or pruning nodes in the evolving architecture of discriminator supports in dealing with catastrophic forgetting problems; a new layer is added to the discriminator when a new concept appears in the data stream. To back these theoretical contributions of SGDOL, experiments were conducted using nine benchmark datasets and compared with ten state-of-the-art online learning algorithms. SGDOL performance measure of testing classification rates was better in seven datasets out of nine than the existing algorithms, which clearly indicates its ability to deal with the data stream.

Publisher Copyright

This research / project is supported by the A*STAR - AME Programmatic Fund (Accelerated Materials Development for Manufacturing Program)
Grant Reference no. : A1898b0043

© 2021 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

https://oar.a-star.edu.sg/communities-collections/articles/18082

978-1-6654-2427-1

Institute for Infocomm Research