On the Role of Reversible Instance Normalization
This work addresses normalization issues in time series forecasting, which is incremental as it revisits and critiques an existing method.
The paper tackled the insufficient understanding of data normalization in time series forecasting by identifying three central challenges: temporal input distribution shift, spatial input distribution shift, and conditional output distribution shift, and found through ablation studies that several components of Reversible Instance Normalization (RevIN) are redundant or detrimental, leading to new perspectives for improving its robustness and generalization.
Data normalization is a crucial component of deep learning models, yet its role in time series forecasting remains insufficiently understood. In this paper, we identify three central challenges for normalization in time series forecasting: temporal input distribution shift, spatial input distribution shift, and conditional output distribution shift. In this context, we revisit the widely used Reversible Instance Normalization (RevIN), by showing through ablation studies that several of its components are redundant or even detrimental. Based on these observations, we draw new perspectives to improve RevIN's robustness and generalization.