Self-supervised Learning for Anomaly Detection in Computational Workflows

TL;DR

This paper presents a self-supervised learning method using autoencoders and graph neural networks to detect anomalies in computational workflows, addressing the scarcity of labeled anomalous data and outperforming existing methods.

Contribution

It introduces a novel self-supervised approach combining generative and contrastive learning for anomaly detection in graph-modeled workflows, handling unlabeled data effectively.

Findings

Outperforms state-of-the-art anomaly detection methods

Effectively models normal behavior in latent space

Handles complex graph dependencies

Abstract

Anomaly detection is the task of identifying abnormal behavior of a system. Anomaly detection in computational workflows is of special interest because of its wide implications in various domains such as cybersecurity, finance, and social networks. However, anomaly detection in computational workflows~(often modeled as graphs) is a relatively unexplored problem and poses distinct challenges. For instance, when anomaly detection is performed on graph data, the complex interdependency of nodes and edges, the heterogeneity of node attributes, and edge types must be accounted for. Although the use of graph neural networks can help capture complex inter-dependencies, the scarcity of labeled anomalous examples from workflow executions is still a significant challenge. To address this problem, we introduce an autoencoder-driven self-supervised learning~(SSL) approach that learns a summary statistic from unlabeled workflow data and estimates the normal behavior of the computational workflow in the latent space. In this approach, we combine generative and contrastive learning objectives to detect outliers in the summary statistics. We demonstrate that by estimating the distribution of normal behavior in the latent space, we can outperform state-of-the-art anomaly detection methods on our benchmark datasets.