English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multivariate time series forecasting has seen widely ranging applications invarious domains, including finance, traffic, energy, and healthcare. To capturethe sophisticated temporal patterns, plenty of research studies designedcomplex neural network architectures based on many variants of RNNs, GNNs, andTransformers. However, complex models are often computationally expensive andthus face a severe challenge in training and inference efficiency when appliedto large-scale real-world datasets. In this paper, we introduce LightTS, alight deep learning architecture merely based on simple MLP-based structures.The key idea of LightTS is to apply an MLP-based structure on top of twodelicate down-sampling strategies, including interval sampling and continuoussampling, inspired by a crucial fact that down-sampling time series oftenpreserves the majority of its information. We conduct extensive experiments oneight widely used benchmark datasets. Compared with the existingstate-of-the-art methods, LightTS demonstrates better performance on five ofthem and comparable performance on the rest. Moreover, LightTS is highlyefficient. It uses less than 5% FLOPS compared with previous SOTA methods onthe largest benchmark dataset. In addition, LightTS is robust and has a muchsmaller variance in forecasting accuracy than previous SOTA methods in longsequence forecasting tasks.

Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures