BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

1 code implementation • NeurIPS 2023 • Zelin Ni, Hang Yu, Shizhan Liu, Jianguo Li, Weiyao Lin

Bases have become an integral part of modern deep learning-based models for time series forecasting due to their ability to act as feature extractors or future references.

Contrastive Learning Self-Supervised Learning +2