Experimental results # 4

* In-Distribution Forecasting

 

To ensure a fair comparison, we adhere to the experimental setting in Time-MoE - fine-tune the pre-trained models on the train split of each benchmark dataset only one epoch. 

 

※ we need to compare with the LLM-based models! (will update soon)

---

< Visualization > 

ETTh1 / ETTh2 96

 

ETTm1 / ETTm2

 

Weather