Outlier absorbing based on a Bayesian approach

TL;DR

This paper introduces a Bayesian-based method that effectively handles outliers in machine learning by combining global and local data perspectives, resulting in robust performance.

Contribution

It proposes a novel outlier absorption technique that integrates global and local views using a Bayesian approach, enhancing robustness against anomalies.

Findings

Demonstrates improved robustness in outlier handling

Shows effectiveness across multiple datasets

Outperforms existing outlier detection methods

Abstract

The presence of outliers is prevalent in machine learning applications and may produce misleading results. In this paper a new method for dealing with outliers and anomal samples is proposed. To overcome the outlier issue, the proposed method combines the global and local views of the samples. By combination of these views, our algorithm performs in a robust manner. The experimental results show the capabilities of the proposed method.