GKM-OD: Gaussian knowledge based modelling for outlier detection
Year: 2025
Type: article
Abstract: Outlier detection is a critical process in data engineering. Leveraging machine learning techniques for outlier detection enables the handling of large-scale, high-dimensional data, enhancing detection accuracy and efficiency. Traditional methods typically model data directly in the data space. However, these approaches often struggle to accurately distinguish inliers from outliers when dealing with complex data distributions. GMM can flexibly fit complex, multi-peak distributions using multiple Gaussian components and effectively identify outliers through probabilistic modelling. We present a novel outlier detection approach that models data indirectly in a latent space using a Gaussian mixture model (GMM) to improve detection efficiency.This approach follows a growing direction in AI, notably advocated by Yann LeCun, which emphasises learning and decision-making in latent representation spaces rather than relying on raw token or feature spaces. For this, we design an encoder-decoder neural network with a GMM as the decision layer, enabling effective identification of outliers through probabilistic modelling. Our method not only addresses practical needs in anomaly detection but also contributes to this broader trend of latent space modelling as a step toward more autonomous and generalisable learning systems. Extensive evaluations on public and proprietary datasets demonstrate that our method outperforms existing approaches, including DAGMM and ECOD, highlighting its superiority in accuracy.
Source: Expert Systems with Applications
Authors: Hui Wang, Haixin Zhong, Gongde Guo
Institutions: Queen's University Belfast, Fujian Normal University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,500
OpenAlex ID: W4416261348