Rethink the Top-u Attention in Sparse Self-attention for Long Sequence Time-Series Forecasting

Xiangxu Meng; Wei Li; Tarek Gaber; Zheng Zhao; Chuhao Chen

doi:10.1007/978-3-031-44223-0_21

ScienceGate Book Chapters

BOOK-CHAPTER

Rethink the Top-u Attention in Sparse Self-attention for Long Sequence Time-Series Forecasting

Xiangxu Meng Wei Li Tarek Gaber Zheng Zhao Chuhao Chen

Year: 2023 Lecture notes in computer science Pages: 256-267 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-031-44223-0_21

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Series (stratigraphy) Quadratic equation Computation Position (finance) Artificial intelligence Sequence (biology) Perspective (graphical) Algorithm Mathematics

Metrics

Cited By

1.32

FWCI (Field Weighted Citation Impact)

Refs

0.81

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Energy Load and Power Forecasting

Physical Sciences → Engineering → Electrical and Electronic Engineering

Time Series Analysis and Forecasting

Physical Sciences → Computer Science → Signal Processing

Stock Market Forecasting Methods

Social Sciences → Decision Sciences → Management Science and Operations Research

Rethink the Top-u Attention in Sparse Self-attention for Long Sequence Time-Series Forecasting

Metrics

Citation History

Topics

Related Documents

Double-Layer Attention for Long Sequence Time-Series Forecasting

Bidformer: A Transformer-Based Model via Bidirectional Sparse Self-Attention Mechanism for Long Sequence Time-Series Forecasting

Enformer: Encoder-Based Sparse Periodic Self-Attention Time-Series Forecasting

Sequence Attention for Multivariate Time Series Forecasting

An improved self-attention for long-sequence time-series data forecasting with missing values