Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles

TL;DR

This paper introduces a diversity-driven neural network ensemble framework for time series classification that promotes feature diversity among models, leading to state-of-the-art results with fewer models and improved efficiency.

Contribution

It proposes a decorrelated learning strategy using feature orthogonality loss to explicitly encourage diversity among ensemble members in TSC.

Findings

Achieves SOTA performance on 128 UCR datasets.

Requires fewer models to reach top accuracy.

Enhances ensemble efficiency and scalability.

Abstract

Ensemble methods have played a crucial role in achieving state-of-the-art (SOTA) performance across various machine learning tasks by leveraging the diversity of features learned by individual models. In Time Series Classification (TSC), ensembles have proven highly effective whether based on neural networks (NNs) or traditional methods like HIVE-COTE. However most existing NN-based ensemble methods for TSC train multiple models with identical architectures and configurations. These ensembles aggregate predictions without explicitly promoting diversity which often leads to redundant feature representations and limits the benefits of ensembling. In this work, we introduce a diversity-driven ensemble learning framework that explicitly encourages feature diversity among neural network ensemble members. Our approach employs a decorrelated learning strategy using a feature orthogonality loss applied directly to the learned feature representations. This ensures that each model in the ensemble captures complementary rather than redundant information. We evaluate our framework on 128 datasets from the UCR archive and show that it achieves SOTA performance with fewer models. This makes our method both efficient and scalable compared to conventional NN-based ensemble approaches.