Transfer Neyman-Pearson Algorithm for Outlier Detection
This addresses a gap in imbalanced classification for outlier detection, offering a practical solution for scenarios with rare abnormal data.
The paper tackles the problem of transfer learning in outlier detection where target abnormal data is scarce, proposing a meta-algorithm that theoretically guarantees robustness to distribution changes and empirically outperforms existing methods for balanced classification.
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).