Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputs

TL;DR

This paper introduces Aux-Net, a scalable deep learning model designed for online classification in environments with inconsistent input features, using ensemble methods and online learning algorithms.

Contribution

It presents a novel auxiliary network architecture that adapts to dynamic inputs and employs online gradient descent and hedging algorithms for scalable, real-time learning.

Findings

Proves effectiveness on public datasets

Handles unreliable and inconsistent input features

Supports single-pass online learning

Abstract

Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios demand is some input features are reliable while others are unreliable or inconsistent. In this paper, we propose a novel deep learning-based model called Auxiliary Network (Aux-Net), which is scalable and agile. It employs a weighted ensemble of classifiers to give a final outcome. The Aux-Net model is based on the hedging algorithm and online gradient descent. It employs a model of varying depth in an online setting using single pass learning. Aux-Net is a foundational work towards scalable neural network model for a dynamic complex environment requiring ad hoc or inconsistent input data. The efficacy of Aux-Net is shown on public dataset.