×
Oct 7, 2021 · SADE consists of two steps: 1) role-guided subgraph embedding, and 2) subgraph anomaly detection. Our approach for learning the subgraph ...
Our extensive experiments on synthetic and real-world financial trans- action networks demonstrate the effectiveness of SADE in learning subgraph embeddings ...
May 26, 2022 · We show empirically that our proposed framework enables the detection of anomalous subgraphs in cryptocurrency transaction networks that go ...
The aim of GAD is to identify anomalous substructures, nodes, or edges within a graph that deviate significantly from the norm, indicating potential ...
People also ask
May 26, 2022 · In this work we are interested in developing novel unsupervised methods for detecting anomalous subgraphs in financial and transaction networks.
This paper introduces a method which is able to detect previously unspecified anomalies in networks, based on a combination of features from network ...
The AntiBenford subgraph, inspired by Benford's Law, is tailored for identifying irregularities in financial transactions. However, it has been known to produce ...
Abstract. Effectively mining anomalous subgraphs in net- works is crucial for various applications, includ- ing disease outbreak detection, financial fraud ...
Chen et al. [4] proposed the AntiBenford subgraph framework for anomaly detection in the Ethereum transaction network under an unsupervised setting. Network- ...
Apr 15, 2024 · GNNs have emerged as a powerful tool for detecting fraudulent activities in complex financial systems because they can analyze the network ...