Journal of Cloud Computing

Advances, Systems and Applications

Table 6 Experimental validation table for generalizability

From: MFGAD-INT: in-band network telemetry data-driven anomaly detection using multi-feature fusion graph deep learning

No.	Method	Precision	Recall	F1
E3/E4	MFGAD-INT	0.9943	0.9995	0.9971
	GDN	0.9053	0.9949	0.9504
	ODS	0.9547	0.9991	0.9767
	RShash	0.7339	0.9508	0.8322
	HSTree	0.6666	0.9994	0.7999
E5/E6	MFGAD-INT	0.9886	0.9974	0.9942
	GDN	0.8375	0.9418	0.8866
	ODS	0.8263	0.9999	0.8969
	RShash	0.7614	0.9999	0.8645
	HSTree	0.5475	0.9993	0.7074
E1/E2	MFGAD-INT	0.9496	0.9999	0.9741
	GDN	0.7893	0.9939	0.8822
	ODS	0.8992	0.9999	0.9469
	RShash	0.6606	0.8727	0.7520
	HSTree	0.3788	0.9593	0.5432

Back to article page