DEVDAN: Deep Evolving Denoising Autoencoder

TL;DR

DEVDAN introduces a deep evolving denoising autoencoder that adapts its structure dynamically for data stream analysis, improving classification performance without fixed network constraints.

Contribution

It presents a novel autoencoder with automatic structure adaptation for data streams, eliminating the need for problem-specific thresholds and enabling single-pass learning.

Findings

Competitive classification accuracy on multiple datasets

Automatic network structure adaptation during data streams

Effective handling of evolving data environments

Abstract

The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of the discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.