Dyformer: A dynamic transformer-based architecture for multivariate time series classification

Chao Yang, Xianzhi Wang, Lina Yao, Guodong Long, Guandong Xu

Abstract: Highlights•We present a transformer-based dynamic architecture to achieve adaptive learning strategies for different frequency components of the time series data.•We design a hierarchical pooling layer to decompose time series into subsequences representing different frequency components to facilitate time series classification.•We implement two types of gates for allowing the architecture to dynamically adapt the layer activation to realize a flexible structure.