Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

TL;DR

This paper introduces Circular Dilated CNN (CDIL-CNN), a symmetric architecture for classifying long sequential data that improves upon existing methods by providing position-wise classification and ensemble capabilities.

Contribution

The paper proposes a novel symmetric multi-scale architecture, CDIL-CNN, that enhances sequence classification by ensuring equal information flow to all positions.

Findings

CDIL-CNN outperforms state-of-the-art methods on various long sequence datasets.

The model provides classification logits at all positions, enabling ensemble learning.

Experimental results demonstrate superior accuracy and robustness.

Abstract

Classification of long sequential data is an important Machine Learning task and appears in many application scenarios. Recurrent Neural Networks, Transformers, and Convolutional Neural Networks are three major techniques for learning from sequential data. Among these methods, Temporal Convolutional Networks (TCNs) which are scalable to very long sequences have achieved remarkable progress in time series regression. However, the performance of TCNs for sequence classification is not satisfactory because they use a skewed connection protocol and output classes at the last position. Such asymmetry restricts their performance for classification which depends on the whole sequence. In this work, we propose a symmetric multi-scale architecture called Circular Dilated Convolutional Neural Network (CDIL-CNN), where every position has an equal chance to receive information from other positions at the previous layers. Our model gives classification logits in all positions, and we can apply a simple ensemble learning to achieve a better decision. We have tested CDIL-CNN on various long sequential datasets. The experimental results show that our method has superior performance over many state-of-the-art approaches.