Transfer Neyman-Pearson Algorithm for Outlier Detection

TL;DR

This paper introduces a transfer learning algorithm tailored for outlier detection in imbalanced data, providing theoretical guarantees and demonstrating superior empirical performance over existing methods.

Contribution

It proposes a novel meta-algorithm for transfer learning in outlier detection with theoretical guarantees and practical instantiations using neural networks.

Findings

The meta-algorithm offers strong theoretical guarantees under distribution shifts.

Neural network-based instantiations outperform traditional transfer methods.

Empirical results show improved outlier detection accuracy in transfer scenarios.

Abstract

We consider the problem of transfer learning in outlier detection where target abnormal data is rare. While transfer learning has been considered extensively in traditional balanced classification, the problem of transfer in outlier detection and more generally in imbalanced classification settings has received less attention. We propose a general meta-algorithm which is shown theoretically to yield strong guarantees w.r.t. to a range of changes in abnormal distribution, and at the same time amenable to practical implementation. We then investigate different instantiations of this general meta-algorithm, e.g., based on multi-layer neural networks, and show empirically that they outperform natural extensions of transfer methods for traditional balanced classification settings (which are the only solutions available at the moment).