A Methodological Report on Anomaly Detection on Dynamic Knowledge Graphs

TL;DR

This paper investigates various machine learning approaches for anomaly detection in dynamic knowledge graphs within Kubernetes micro-services, proposing an ensemble method that outperforms baselines on a relevant dataset.

Contribution

It introduces a novel ensemble learning approach combining multiple models on different graph representations for improved anomaly detection.

Findings

Ensemble learning significantly improves detection accuracy.

Hierarchical data representation enhances model performance.

The method outperforms baseline models on the ISWC 2024 dataset.

Abstract

In this paper, we explore different approaches to anomaly detection on dynamic knowledge graphs, specifically in a Micro-services environment for Kubernetes applications. Our approach explores three dynamic knowledge graph representations: sequential data, hierarchical data and inter-service dependency data, with each representation incorporating increasingly complex structural information of dynamic knowledge graph. Different machine learning and deep learning models are tested on these representations. We empirically analyse their performance and propose an approach based on ensemble learning of these models. Our approach significantly outperforms the baseline on the ISWC 2024 Dynamic Knowledge Graph Anomaly Detection dataset, providing a robust solution for anomaly detection in dynamic complex data.