arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07579cs.LG
收藏

通过多样性驱动的神经网络集成增强时间序列分类

Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles

Université de Haute Alsace(阿尔萨斯大学);IRIMAS;Monash University(墨尔本大学);DSAI(数据科学与人工智能学院)

Javidan Abdullayev, Maxime Devanne, Cyril Meyer, Ali Ismail-Fawaz, Jonathan Weber, Germain Forestier

AI总结:

本文提出了一种多样性驱动的神经网络集成框架,通过特征正交损失促进特征多样性,从而在时间序列分类中实现更高效和可扩展的集成学习。

摘要:

集成方法通过利用单个模型学习的特征多样性,在各种机器学习任务中发挥了关键作用,实现了最先进的性能。在时间序列分类(TSC)中,集成方法无论是基于神经网络(NNs)还是传统方法如HIVE-COTE,都证明了其高度有效性。然而,大多数现有的基于神经网络的TSC集成方法训练多个具有相同架构和配置的模型。这些集成在聚合预测时没有显式促进多样性,这通常导致冗余的特征表示,并限制了集成的优势。在本文中,我们引入了一个以多样性驱动的集成学习框架,该框架明确鼓励神经网络集成成员之间的特征多样性。我们的方法采用一种去相关学习策略,通过直接应用于学习的特征表示的特征正交损失来实现。这确保了集成中的每个模型捕捉互补而非冗余的信息。我们在UCR档案中的128个数据集上评估了我们的框架,并展示了其在较少模型的情况下实现了最先进的性能。这使得我们的方法在效率和可扩展性上都优于传统基于神经网络的集成方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑