Messages are Never Propagated Alone: Collaborative Hypergraph Neural Network for Time-Series Forecasting

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 46; no. 4; pp. 1 - 15
• Main Authors: Yin, Nan, Shen, Li, Xiong, Huan, Gu, Bin, Chen, Chong, Hua, Xian-Sheng, Liu, Siwei, Luo, Xiao
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Collaboration; Convolution; Correlated time series forecasting; Correlation; Data models; Demand analysis; Feature maps; Forecasting; Graph theory; Graphs; hypergraph; hypergraph neural network; Interaction models; Mathematical models; Message passing; Messages; Neural networks; Social networks; Time series; Time series analysis

This paper delves into the problem of correlated time-series forecasting in practical applications, an area of growing interest in a multitude of fields such as stock price prediction and traffic demand analysis. Current methodologies primarily represent data using conventional graph structures, yet...