How to boost autoencoders?
This work addresses a specific technical problem for machine learning practitioners using autoencoders, but it appears incremental as it adapts existing boosting methods to a particular neural network type.
The paper tackled the challenge of boosting autoencoders by proposing a framework to overcome associated issues, enabling performance gains in anomaly detection and clustering applications.
Autoencoders are a category of neural networks with applications in numerous domains and hence, improvement of their performance is gaining substantial interest from the machine learning community. Ensemble methods, such as boosting, are often adopted to enhance the performance of regular neural networks. In this work, we discuss the challenges associated with boosting autoencoders and propose a framework to overcome them. The proposed method ensures that the advantages of boosting are realized when either output (encoded or reconstructed) is used. The usefulness of the boosted ensemble is demonstrated in two applications that widely employ autoencoders: anomaly detection and clustering.