Highly Imbalanced Regression with Tabular Data in SEP and Other Applications
This addresses the challenge of accurately predicting rare instances in regression tasks for applications like space weather forecasting, representing an incremental improvement over existing methods.
The paper tackles the problem of highly imbalanced regression in tabular data, such as forecasting rare Solar Energetic Particle events, by proposing CISIR, which achieves lower error and higher correlation compared to recent methods on five datasets.
We investigate imbalanced regression with tabular data that have an imbalance ratio larger than 1,000 ("highly imbalanced"). Accurately estimating the target values of rare instances is important in applications such as forecasting the intensity of rare harmful Solar Energetic Particle (SEP) events. For regression, the MSE loss does not consider the correlation between predicted and actual values. Typical inverse importance functions allow only convex functions. Uniform sampling might yield mini-batches that do not have rare instances. We propose CISIR that incorporates correlation, Monotonically Decreasing Involution (MDI) importance, and stratified sampling. Based on five datasets, our experimental results indicate that CISIR can achieve lower error and higher correlation than some recent methods. Also, adding our correlation component to other recent methods can improve their performance. Lastly, MDI importance can outperform other importance functions. Our code can be found in https://github.com/Machine-Earning/CISIR.