A Complex Heterogeneous Network Model of Disease Regulated by Noncoding RNAs: A Case Study of Unstable Angina Pectoris

Table 5

Results of parameter optimization experiments calculated by MR and MRR.

Epoch	25	50	100	200
MR	10.3123 ± 1.9440	7.9155 ± 0.7216	8.3054 ± 0.8194	8.155 ± 0.7939
MRR	0.1000 ± 0.0177	0.1274 ± 0.0134	0.1215 ± 0.0123	0.1236 ± 0.0115
Embedding	32	64	96	128
MR	9.0563 ± 0.7624	7.9155 ± 0.7216	8.1209 ± 0.8165	7.9137 ± 0.8641
MRR	0.1111 ± 0.0091	0.1274 ± 0.0134	0.1243 ± 0.0131	0.1276 ± 0.0131
Learning rate	0.0001	0.001	0.01	0.1
MR	44.1148 ± 7.67	7.9155 ± 0.7216	9.0002 ± 0.8692	10.4498 ± 1.0269
MRR	0.0234 ± 0.0046	0.1274 ± 0.0134	0.1120 ± 0.0107	0.0966 ± 0.0101

The bold values indicate the best parameters and the resulting best results.