Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models

TL;DR

This paper introduces a framework that transforms context-dependent anomaly detection into a link prediction problem using knowledge graph embeddings, enhancing anomaly detection accuracy by leveraging semantic context.

Contribution

The paper presents a novel framework converting context-dependent anomaly detection into link prediction, enabling the use of knowledge graph embedding models for improved detection.

Findings

High accuracy in detecting context-dependent anomalies

Effective use of knowledge graph embeddings for anomaly detection

Object detectors provide sufficient context for the framework

Abstract

Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this work, we leverage contextual awareness for the anomaly detection problem. Although graphed-based anomaly detection has been widely studied, context-dependent anomaly detection is an open problem and without much current research. We develop a general framework for converting a context-dependent anomaly detection problem to a link prediction problem, allowing well-established techniques from this domain to be applied. We implement a system based on our framework that utilizes knowledge graph embedding models and demonstrates the ability to detect outliers using context provided by a semantic knowledge base. We show that our method can detect context-dependent anomalies with a high degree of accuracy and show that current object detectors can detect enough classes to provide the needed context for good performance within our example domain.