Composite Neural Network: Theory and Application to PM2.5 Prediction

TL;DR

This paper develops a theoretical framework for composite neural networks, proving their performance advantages over individual components, and demonstrates their effectiveness in PM2.5 air quality prediction.

Contribution

The paper introduces a novel framework for composite neural networks, providing theoretical guarantees of performance improvements and validating them through PM2.5 prediction experiments.

Findings

Composite neural networks outperform individual pre-trained models with high probability.

Adding extra pre-trained components does not degrade overall performance.

Empirical results show superior accuracy in PM2.5 prediction compared to other models.

Abstract

This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well trained, targeted to approximate a specific function. Despite a general belief that a composite neural network may perform better than a single component, the overall performance characteristics are not clear. In this work, we construct the framework of a composite network, and prove that a composite neural network performs better than any of its pre-trained components with a high probability bound. In addition, if an extra pre-trained component is added to a composite network, with high probability, the overall performance will not be degraded. In the study, we explore a complicated application -- PM2.5 prediction -- to illustrate the correctness of the proposed composite network theory. In the empirical evaluations of PM2.5 prediction, the constructed composite neural network models support the proposed theory and perform better than other machine learning models, demonstrate the advantages of the proposed framework.