Multipattern Integrated Networks With Contrastive Pretraining for Graph Anomaly Detection
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Computational Social Systems"
DOI: 10.1109/tcss.2024.3362393
Abstract: As a challenge of practical significance, fraud detection has great potential for telecom fraud prevention, economic crime prevention, and personal property preservation. Fraudulent activities are always buried in massive regular transactions, making it hard to… read more here.
Keywords: detection; contrastive pretraining; integrated networks; multipattern integrated ... See more keywords