Anomaly Detection using GNNs
Dnr:
NAISS 2024/22-1376
Type:
NAISS Small Compute
Principal Investigator:
Nancy Xu
Affiliation:
Kungliga Tekniska högskolan
Start Date:
2024-10-30
End Date:
2025-11-01
Primary Classification:
20299: Other Electrical Engineering, Electronic Engineering, Information Engineering
Webpage:
Allocation
Abstract
GNNs have seen great success in natural language processing and signal processing. We have investigated whether such results can be generalized to a broader range of time series by proposing a novel method of graph construction based on temporal relationships. This project aims to continue this work by applying this method to time series anomaly detection along with further work in explainability of these results.