DEVDAN: Deep Evolving Denoising Autoencoder
This addresses the need for adaptive data stream analytics in machine learning, though it appears incremental as it builds on existing DAE methods.
The paper tackles the problem of Denoising Autoencoders (DAE) having fixed network capacity that cannot adapt to rapidly changing data streams, and proposes DEVDAN, which automatically adds and discards hidden units on the fly, achieving competitive network architecture compared to state-of-the-art methods on ten datasets.
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.