Relationship Discovery and Hierarchical Embedding for Web Service Quality Prediction

Table 2

Overall performance comparison of RT on average.

Method	MAE/matrix density						RMSE/matrix density
	0.10	0.15	0.20	0.25	0.30	Average	0.10	0.15	0.20	0.25	0.30	Average
LDA	0.49	0.46	0.45	0.43	0.42	0.4500	1.48	1.45	1.44	1.43	1.41	1.4420
Node2vec	0.44	0.43	0.41	0.40	0.39	0.4140	1.43	1.41	1.4	1.38	1.37	1.3980
GCN	0.45	0.43	0.43	0.42	0.41	0.4280	1.47	1.45	1.43	1.41	1.39	1.4300
Wide & deep	0.42	0.41	0.39	0.38	0.37	0.3975	1.39	1.36	1.32	1.30	1.28	1.3300
GraphSAGE	0.41	0.4	0.38	0.37	0.36	0.3840	1.38	1.37	1.35	1.34	1.32	1.3520
NGCF	0.4	0.38	0.37	0.38	0.36	0.3780	1.37	1.36	1.35	1.34	1.33	1.3500
PinSage	0.4	0.38	0.36	0.36	0.35	0.3700	1.35	1.34	1.32	1.31	1.30	1.3240
KGAT	0.39	0.38	0.37	0.36	0.35	0.3700	1.31	1.29	1.27	1.26	1.25	1.2760
GraphRec	0.38	0.36	0.35	0.35	0.34	0.3560	1.3	1.27	1.25	1.23	1.22	1.2540
NIA-GCN	0.39	0.36	0.34	0.33	0.32	0.3480	1.29	1.26	1.23	1.22	1.21	1.2420
RDHE	0.37	0.35	0.34	0.32	0.3	0.3360	1.24	1.22	1.21	1.20	1.20	1.2140