Meta-Learning for Unsupervised Outlier Detection with Optimal Transport

TL;DR

This paper introduces a meta-learning approach utilizing optimal transport to automate unsupervised outlier detection by selecting the most suitable technique based on data distribution similarities, outperforming existing methods.

Contribution

It presents a novel meta-learning framework that leverages optimal transport to improve unsupervised outlier detection by matching datasets with similar distributions.

Findings

Outperforms state-of-the-art outlier detection methods

Robustness demonstrated across diverse datasets

Generalizable approach for other unsupervised tasks

Abstract

Automated machine learning has been widely researched and adopted in the field of supervised classification and regression, but progress in unsupervised settings has been limited. We propose a novel approach to automate outlier detection based on meta-learning from previous datasets with outliers. Our premise is that the selection of the optimal outlier detection technique depends on the inherent properties of the data distribution. We leverage optimal transport in particular, to find the dataset with the most similar underlying distribution, and then apply the outlier detection techniques that proved to work best for that data distribution. We evaluate the robustness of our approach and find that it outperforms the state of the art methods in unsupervised outlier detection. This approach can also be easily generalized to automate other unsupervised settings.