RandomNet: Clustering Time Series Using Untrained Deep Neural Networks

TL;DR

RandomNet introduces a novel, training-free clustering method for time series that leverages untrained neural networks with random weights to generate diverse representations, enabling effective clustering across varied datasets.

Contribution

It proposes a new untrained neural network approach for time series clustering, eliminating the need for training and demonstrating competitive performance.

Findings

Effective clustering on diverse time series datasets.

No training required due to random weight initialization.

Competitive results compared to state-of-the-art methods.

Abstract

Neural networks are widely used in machine learning and data mining. Typically, these networks need to be trained, implying the adjustment of weights (parameters) within the network based on the input data. In this work, we propose a novel approach, RandomNet, that employs untrained deep neural networks to cluster time series. RandomNet uses different sets of random weights to extract diverse representations of time series and then ensembles the clustering relationships derived from these different representations to build the final clustering results. By extracting diverse representations, our model can effectively handle time series with different characteristics. Since all parameters are randomly generated, no training is required during the process. We provide a theoretical analysis of the effectiveness of the method. To validate its performance, we conduct extensive experiments on all of the 128 datasets in the well-known UCR time series archive and perform statistical analysis of the results. These datasets have different sizes, sequence lengths, and they are from diverse fields. The experimental results show that the proposed method is competitive compared with existing state-of-the-art methods.