Error Distribution Smoothing:Advancing Low-Dimensional Imbalanced Regression

TL;DR

This paper introduces Error Distribution Smoothing (EDS), a novel method for imbalanced regression that addresses data scarcity in high-complexity regions by selecting representative data subsets, improving regression performance.

Contribution

The paper proposes a new concept of Imbalanced Regression and introduces EDS, a method that effectively balances data representation in imbalanced regression tasks.

Findings

EDS effectively reduces data redundancy and improves regression accuracy.

Experimental results demonstrate EDS's superiority over existing methods.

Code and datasets are publicly available for reproducibility.

Abstract

In real-world regression tasks, datasets frequently exhibit imbalanced distributions, characterized by a scarcity of data in high-complexity regions and an abundance in low-complexity areas. This imbalance presents significant challenges for existing classification methods with clear class boundaries, while highlighting a scarcity of approaches specifically designed for imbalanced regression problems. To better address these issues, we introduce a novel concept of Imbalanced Regression, which takes into account both the complexity of the problem and the density of data points, extending beyond traditional definitions that focus only on data density. Furthermore, we propose Error Distribution Smoothing (EDS) as a solution to tackle imbalanced regression, effectively selecting a representative subset from the dataset to reduce redundancy while maintaining balance and representativeness. Through several experiments, EDS has shown its effectiveness, and the related code and dataset can be accessed at https://anonymous.4open.science/r/Error-Distribution-Smoothing-762F.