Skip to content

ReGuider

Home / Concepts / ReGuider

ReGuider

Auto-generated stub. Edit this file to add more details.

A plug-in method that uses representation-level supervision from a pretrained teacher model to guide the encoder training of a target time series forecasting model.

Why It Matters

It is the proposed novel plug-in method that introduces representation-level supervision for improving time series forecasting encoders.

Evidence

we propose ReGuider, a plug-in method that can be seamlessly integrated into any forecasting architecture.

Metadata & Links