Random Walk-steered Majority Undersampling

TL;DR

This paper introduces RWMaU, a novel undersampling method that uses random walks to identify and undersample majority class points close to minority classes, improving class imbalance handling.

Contribution

The paper presents a new undersampling technique leveraging random walk proximity to better identify majority points near minority classes.

Findings

Significant performance improvements over existing methods.

Effective on diverse datasets and classifiers.

Reduces class imbalance impact in practical scenarios.

Abstract

In this work, we propose Random Walk-steered Majority Undersampling (RWMaU), which undersamples the majority points of a class imbalanced dataset, in order to balance the classes. Rather than marking the majority points which belong to the neighborhood of a few minority points, we are interested to perceive the closeness of the majority points to the minority class. Random walk, a powerful tool for perceiving the proximities of connected points in a graph, is used to identify the majority points which lie close to the minority class of a class-imbalanced dataset. The visit frequencies and the order of visits of the majority points in the walks enable us to perceive an overall closeness of the majority points to the minority class. The ones lying close to the minority class are subsequently undersampled. Empirical evaluation on 21 datasets and 3 classifiers demonstrate substantial improvement in performance of RWMaU over the competing methods.