SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning
This work proposes SIFT, a robust adaptation method that enhances time series foundation models by preserving Semantic Invariance and structural Fidelity throughout the fine-Tuning process, and implements a component-based structural fidelity enhancement.
Yi Tang, Teng-Xue Zhang, Yang Shu et al.
· 0 citations