Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles

2025-06-30

IEEE International Joint Conference on Neural Network

AI Summary

Existing neural network ensemble methods for time series classification often lack explicit mechanisms to enforce diversity, leading to feature redundancy among constituent models and limiting overall ensemble performance. To address this limitation, this work proposes a diversity-driven ensemble framework that introduces, for the first time in this task, a feature orthogonality loss to explicitly encourage member models to learn complementary feature representations through decorrelated learning. Evaluated on 128 UCR benchmark datasets, the proposed method achieves state-of-the-art performance with fewer ensemble members, significantly improving classification accuracy, computational efficiency, and scalability compared to existing approaches.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Representation Learning for Vision
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

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.

Problem

• Time Series Classification
• Neural Network Ensembles
• Feature Diversity
• Ensemble Redundancy
• Model Diversity

Innovation

• diversity-driven ensemble
• feature orthogonality loss
• time series classification
• neural network ensemble
• decorrelated learning