Volume 12 - Issue 1
Temporal Patterns Discovery of Evolving Graphs for Graph Neural Network (GNN)-based Anomaly Detection in Heterogeneous Networks
- Jongmo Kim
Department of Industrial Engineering, Sungkyunkwan University, Suwon, South Korea
dignityc@skku.edu
- Kunyoung Kim
Department of Industrial Engineering, Sungkyunkwan University, Suwon, South Korea
kimkun0@skku.edu
- Gi-yoon Jeon
R&D Institute, Agency for Defense Development, Seoul, South Korea
gyjeon@add.re.kr
- Mye Sohn
Department of Industrial Engineering, Sungkyunkwan University, Suwon, South Korea
myesohn@skku.edu
Keywords: Graph-based Anomaly Detection, Evolving Graphs, GNN, Attributed Networks, Heterogeneous Networks
Abstract
This paper proposes a new method named evolving-graph generation framework to simultaneously
solve the complexity and dynamic nature of the attribute networks that can occur in graph-based
anomaly detection with Graph Neural Networks (GNN). The proposed framework consists of two
components. The first component is a feature selection method that hybridizes filter-based and
wrapper-based techniques to reduce the snapshots. The second component is an association method
based on temporal patterns for the snapshots using the subgraph embedding technique and gaussianbase
KL divergence. At the time, the association method finds intra-snapshots and inter-snapshots
associations. As a result, we can obtain an evolving graph that is simplified and temporal patternsenhanced
from original networks. It is used an input graph for a GNN-based anomaly detection
model. To show the superiority of the proposed framework, we conduct experiments and evaluations
on 8 real-world datasets with anomaly labels with comparative state-of-the-art models of graph-based
anomaly detection. We show that the proposed framework outperforms state-of-the-art methods in
the accuracy and stability of training with the trend of decreasing train loss.