A Graph Prompt Fine-Tuning Method for WSN Spatio-Temporal Correlation Anomaly Detection

TL;DR

This paper introduces a graph prompt fine-tuning approach for anomaly detection in WSNs, leveraging spatio-temporal features and self-supervised learning to improve detection accuracy and reduce training costs.

Contribution

It proposes a novel graph neural network backbone with a multi-task self-supervised training strategy and a graph prompting mechanism for effective anomaly detection in WSN data.

Findings

Achieved F1 scores of 91.30% on public dataset and 92.31% on real data.

Outperformed existing methods in detection accuracy and generalization.

Reduced training costs through self-supervised pre-training and fine-tuning.

Abstract

Anomaly detection of multi-temporal modal data in Wireless Sensor Network (WSN) can provide an important guarantee for reliable network operation. Existing anomaly detection methods in multi-temporal modal data scenarios have the problems of insufficient extraction of spatio-temporal correlation features, high cost of anomaly sample category annotation, and imbalance of anomaly samples. In this paper, a graph neural network anomaly detection backbone network incorporating spatio-temporal correlation features and a multi-task self-supervised training strategy of "pre-training - graph prompting - fine-tuning" are designed for the characteristics of WSN graph structure data. First, the anomaly detection backbone network is designed by improving the Mamba model based on a multi-scale strategy and inter-modal fusion method, and combining it with a variational graph convolution module, which is capable of fully extracting spatio-temporal correlation features in the multi-node, multi-temporal modal scenarios of WSNs. Secondly, we design a three-subtask learning "pre-training" method with no-negative comparative learning, prediction, and reconstruction to learn generic features of WSN data samples from unlabeled data, and design a "graph prompting-fine-tuning" mechanism to guide the pre-trained self-supervised learning. The model is fine-tuned through the "graph prompting-fine-tuning" mechanism to guide the pre-trained self-supervised learning model to complete the parameter fine-tuning, thereby reducing the training cost and enhancing the detection generalization performance. The F1 metrics obtained from experiments on the public dataset and the actual collected dataset are up to 91.30% and 92.31%, respectively, which provides better detection performance and generalization ability than existing methods designed by the method.