Outlier Detection through Null Space Analysis of Neural Networks

TL;DR

This paper introduces NuSA, a neural network-based outlier detection method that integrates null space analysis directly into the classification model, maintaining performance while effectively identifying outliers.

Contribution

The paper presents a novel null space analysis technique that embeds outlier detection within neural networks, simplifying the process by avoiding separate models.

Findings

NuSA maintains classification accuracy.

NuSA detects outliers effectively.

Outlier detection rates are comparable to existing methods.

Abstract

Many machine learning classification systems lack competency awareness. Specifically, many systems lack the ability to identify when outliers (e.g., samples that are distinct from and not represented in the training data distribution) are being presented to the system. The ability to detect outliers is of practical significance since it can help the system behave in an reasonable way when encountering unexpected data. In prior work, outlier detection is commonly carried out in a processing pipeline that is distinct from the classification model. Thus, for a complete system that incorporates outlier detection and classification, two models must be trained, increasing the overall complexity of the approach. In this paper we use the concept of the null space to integrate an outlier detection method directly into a neural network used for classification. Our method, called Null Space Analysis (NuSA) of neural networks, works by computing and controlling the magnitude of the null space projection as data is passed through a network. Using these projections, we can then calculate a score that can differentiate between normal and abnormal data. Results are shown that indicate networks trained with NuSA retain their classification performance while also being able to detect outliers at rates similar to commonly used outlier detection algorithms.