English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Along with the rapid evolution of mobile communication technologies, such as5G, there has been a drastically increase in telecom fraud, which significantlydissipates individual fortune and social wealth. In recent years, graph miningtechniques are gradually becoming a mainstream solution for detecting telecomfraud. However, the graph imbalance problem, caused by the Pareto principle,brings severe challenges to graph data mining. This is a new and challengingproblem, but little previous work has been noticed. In this paper, we propose aGraph ATtention network with COst-sensitive BOosting (GAT-COBO) for the graphimbalance problem. First, we design a GAT-based base classifier to learn theembeddings of all nodes in the graph. Then, we feed the embeddings into awell-designed cost-sensitive learner for imbalanced learning. Next, we updatethe weights according to the misclassification cost to make the model focusmore on the minority class. Finally, we sum the node embeddings obtained bymultiple cost-sensitive learners to obtain a comprehensive node representation,which is used for the downstream anomaly detection task. Extensive experimentson two real-world telecom fraud detection datasets demonstrate that ourproposed method is effective for the graph imbalance problem, outperforming thestate-of-the-art GNNs and GNN-based fraud detectors. In addition, our model isalso helpful for solving the widespread over-smoothing problem in GNNs. TheGAT-COBO code and datasets are available at https://github.com/xxhu94/GAT-COBO.

GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection