Ensemble Transitive Bidirectional Decoupled Self-Distillation for Time-Series Classification

Numerous existing deep learning models for time-series classification (TSC) tend to overlook the intricate interplay between higher-and lower-level semantic information. While the focus is often on extracting higher-level semantics from lower-level sources, the reciprocal influence of lower-level information on higher levels is undervalued. To address this, we propose an ensemble transitive bidirectional decoupled self-distillation (ETBiDecSD) method for TSC. ETBiDecSD enhances the robustness of higher-level semantic information using an average feature ensemble (AFE) method to amalgamate the output from each level. Simultaneously, the integrated features are transmitted to each lower level through a…

• NS
  Natural Science Foundation of Hebei Province

  Award: F2022105027
• SJ
  Southwest Jiaotong University
• FR
  Fundamental Research Funds for the Central Universities
• UO
  University of Nottingham Ningbo China