Residual-enhanced graph convolutional networks with hypersphere mapping for anomaly detection in attributed networks

In the burgeoning field of anomaly detection within attributed networks, traditional methodologies often encounter the intricacies of network complexity, particularly in capturing nonlinearity and sparsity. This study introduces an innovative approach that synergizes the strengths of graph convoluti...

وصف كامل

التفاصيل البيبلوغرافية

الحاوية / القاعدة:	Data Science and Management
المؤلفون الرئيسيون:	Wasim Khan, Afsaruddin Mohd, Mohammad Suaib, Mohammad Ishrat, Anwar Ahamed Shaikh, Syed Mohd Faisal
التنسيق:	مقال
اللغة:	الإنجليزية
منشور في:	KeAi Communications Co. Ltd. 2025-06-01
الموضوعات:	Anomaly detection Deep learning Hypersphere learning Residual modeling Graph convolution network Attention mechanism
الوصول للمادة أونلاين:	http://www.sciencedirect.com/science/article/pii/S2666764924000481