MONSTER: Monash Scalable Time Series Evaluation Repository

TL;DR

MONSTER is a large-scale time series dataset repository designed to expand benchmarking and foster progress in scalable time series classification beyond small datasets.

Contribution

It introduces a new collection of large datasets for time series classification, addressing the limitations of existing small benchmarks and encouraging research on scalable models.

Findings

Provides large datasets for benchmarking

Highlights the need for scalable time series models

Encourages research on large-scale data learning

Abstract

We introduce MONSTER-the MONash Scalable Time Series Evaluation Repository-a collection of large datasets for time series classification. The field of time series classification has benefitted from common benchmarks set by the UCR and UEA time series classification repositories. However, the datasets in these benchmarks are small, with median sizes of 217 and 255 examples, respectively. In consequence they favour a narrow subspace of models that are optimised to achieve low classification error on a wide variety of smaller datasets, that is, models that minimise variance, and give little weight to computational issues such as scalability. Our hope is to diversify the field by introducing benchmarks using larger datasets. We believe that there is enormous potential for new progress in the field by engaging with the theoretical and practical challenges of learning effectively from larger quantities of data.