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

Long-term time series forecasting (LTSF) is a crucial aspect of modernsociety, playing a pivotal role in facilitating long-term planning anddeveloping early warning systems. While many Transformer-based models haverecently been introduced for LTSF, a doubt have been raised regarding theeffectiveness of attention modules in capturing cross-time dependencies. Inthis study, we design a mask-series experiment to validate this assumption andsubsequently propose the "Cross-variable Linear Integrated ENhanced Transformerfor Multivariate Long-Term Time Series Forecasting" (Client), an advanced modelthat outperforms both traditional Transformer-based models and linear models.Client employs linear modules to learn trend information and attention modulesto capture cross-variable dependencies. Meanwhile, it simplifies the embeddingand position encoding layers and replaces the decoder module with a projectionlayer. Essentially, Client incorporates non-linearity and cross-variabledependencies, which sets it apart from conventional linear models andTransformer-based models. Extensive experiments with nine real-world datasetshave confirmed the SOTA performance of Client with the least computation timeand memory consumption compared with the previous Transformer-based models. Ourcode is available at https://github.com/daxin007/Client.

Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series Forecasting