A Methodological Report on Anomaly Detection on Dynamic Knowledge Graphs
This work addresses anomaly detection in dynamic knowledge graphs for Kubernetes micro-services, which is an incremental improvement in a domain-specific application.
The paper tackled anomaly detection on dynamic knowledge graphs in Kubernetes micro-services environments by testing various machine learning and deep learning models on three different graph representations and proposing an ensemble learning approach. Their method significantly outperformed the baseline on the ISWC 2024 dataset, providing a robust solution for this complex data.
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.