Inner-Instance Normalization for Time Series Forecasting
This addresses a specific bottleneck in time series forecasting for applications dealing with non-stationary data, though it is incremental relative to existing instance normalization techniques.
The paper tackles inner-instance distribution shifts in time series forecasting by proposing two point-level methods, LD and LCD, which improve model performance across public benchmarks.
Real-world time series are influenced by numerous factors and exhibit complex non-stationary characteristics. Non-stationarity can lead to distribution shifts, where the statistical properties of time series change over time, negatively impacting model performance. Several instance normalization techniques have been proposed to address distribution shifts in time series forecasting. However, existing methods fail to account for shifts within individual instances, leading to suboptimal performance. To tackle inner-instance distribution shifts, we propose two novel point-level methods: Learning Distribution (LD) and Learning Conditional Distribution (LCD). LD eliminates internal discrepancies by fitting the internal distribution of input and output with different parameters at different time steps, while LCD utilizes neural networks to predict scaling coefficients of the output. We evaluate the performance of the two methods with various backbone models across public benchmarks and demonstrate the effectiveness of the point-level paradigm through comparative experiments.