Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysis

TL;DR

This paper proposes TopoGDN, a novel multivariate time-series anomaly detection model that enhances Graph Attention Networks with topological analysis to better capture complex dependencies across time and features.

Contribution

The paper introduces a multi-scale temporal convolution and an augmented GAT incorporating graph topology, improving anomaly detection in multivariate time series.

Findings

Outperforms baseline models on four datasets

Effectively captures complex inter-feature dependencies

Demonstrates robustness in diverse industrial scenarios

Abstract

Unsupervised anomaly detection in time series is essential in industrial applications, as it significantly reduces the need for manual intervention. Multivariate time series pose a complex challenge due to their feature and temporal dimensions. Traditional methods use Graph Neural Networks (GNNs) or Transformers to analyze spatial while RNNs to model temporal dependencies. These methods focus narrowly on one dimension or engage in coarse-grained feature extraction, which can be inadequate for large datasets characterized by intricate relationships and dynamic changes. This paper introduces a novel temporal model built on an enhanced Graph Attention Network (GAT) for multivariate time series anomaly detection called TopoGDN. Our model analyzes both time and feature dimensions from a fine-grained perspective. First, we introduce a multi-scale temporal convolution module to extract detailed temporal features. Additionally, we present an augmented GAT to manage complex inter-feature dependencies, which incorporates graph topology into node features across multiple scales, a versatile, plug-and-play enhancement that significantly boosts the performance of GAT. Our experimental results confirm that our approach surpasses the baseline models on four datasets, demonstrating its potential for widespread application in fields requiring robust anomaly detection. The code is available at https://github.com/ljj-cyber/TopoGDN.