Towards Fair Deep Anomaly Detection
This work is significant for researchers and practitioners using deep anomaly detection, as it highlights and provides a solution for potential social biases in these models, ensuring more equitable outcomes.
This paper addresses the issue of social bias in deep one-class classification for anomaly detection, where deep learning models might inadvertently learn patterns correlated with sensitive attributes. The authors propose Deep Fair SVDD, an adversarial network architecture that de-correlates sensitive attributes from learned representations, achieving significant fairness improvements with minimal impact on anomaly detection performance.
Anomaly detection aims to find instances that are considered unusual and is a fundamental problem of data science. Recently, deep anomaly detection methods were shown to achieve superior results particularly in complex data such as images. Our work focuses on deep one-class classification for anomaly detection which learns a mapping only from the normal samples. However, the non-linear transformation performed by deep learning can potentially find patterns associated with social bias. The challenge with adding fairness to deep anomaly detection is to ensure both making fair and correct anomaly predictions simultaneously. In this paper, we propose a new architecture for the fair anomaly detection approach (Deep Fair SVDD) and train it using an adversarial network to de-correlate the relationships between the sensitive attributes and the learned representations. This differs from how fairness is typically added namely as a regularizer or a constraint. Further, we propose two effective fairness measures and empirically demonstrate that existing deep anomaly detection methods are unfair. We show that our proposed approach can remove the unfairness largely with minimal loss on the anomaly detection performance. Lastly, we conduct an in-depth analysis to show the strength and limitations of our proposed model, including parameter analysis, feature visualization, and run-time analysis.