no code implementations • 17 Jan 2024 • Zongjiang Shang, Ling Chen
In addition, a tri-stage message passing mechanism is introduced to aggregate pattern information and learn the interaction strength between temporal patterns of different scales.
2 code implementations • 13 Jan 2022 • Ling Chen, Donghui Chen, Zongjiang Shang, Binqing Wu, Cen Zheng, Bo Wen, Wei zhang
Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies.
1 code implementation • 14 Dec 2021 • Donghui Chen, Ling Chen, Zongjiang Shang, Youdong Zhang, Bo Wen, Chenghu Yang
In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF).