Table 2 Open in new tab Three types of...

Type of parameters analyzed

Models performing the analysis

Matrix decomposition/completion-related parameters

The regularization coefficients in the objective function

MLPMDA [21]

M2LFL [10]

NIMCGCN [28]

TDRC [30]

The dimensionality parameter for latent feature representation matrices of miRNAs and diseases

M2LFL [10]

GRNMF [20]

TDRC [30]

The number of computation layers for matrix decomposition/completion

MLPMDA [21]

The maximum number of iterations for optimizing the objective function

GRNMF [20]

Deep learning-related parameters

The regularization coefficients in the loss function

M2LFL [10]

GRNMF [20]

The size of miRNA and disease embeddings

AEMDA [17]

MMGCN [9]

GAEMDA [37]

The learning rate

MMGCN [9]

The number of filters in convolutional neural network

MMGCN [9]

The number of neural network layers

MVMTMDA [15]

MMGCN [9]

NMCMDA [36]

GAEMDA [37]

NIMCGCN [28]

The negative sampling ratio

MVMTMDA [15]

miRNA- and disease-related parameters

MiRNAs and diseases’ k nearest neighbours, whose similarity features were used to update the MDA adjacency matrix

MLPMDA [21]

GRNMF [20]

Weights for constructing integrated similarity matrices of miRNAs and diseases

MLPMDA [21]

AEMDA [17]

Parameter k of the KNN classifier for constructing the edges between the MDP nodes in the homogeneous graph

MDA–GCNFTG [32]

Table 2

Open in new tab

Three types of parameters summarized from the procedures of parameter sensitivity analysis by 11 state-of-the-art computational models

Type of parameters analyzed	Models performing the analysis
Matrix decomposition/completion-related parameters
The regularization coefficients in the objective function	MLPMDA [21]
	M2LFL [10]
	NIMCGCN [28]
	TDRC [30]
The dimensionality parameter for latent feature representation matrices of miRNAs and diseases	M2LFL [10]
	GRNMF [20]
	TDRC [30]
The number of computation layers for matrix decomposition/completion	MLPMDA [21]
The maximum number of iterations for optimizing the objective function	GRNMF [20]
Deep learning-related parameters
The regularization coefficients in the loss function	M2LFL [10]
The regularization coefficients in the loss function	GRNMF [20]
The size of miRNA and disease embeddings	AEMDA [17]
	MMGCN [9]
	GAEMDA [37]
The learning rate	MMGCN [9]
The number of filters in convolutional neural network	MMGCN [9]
The number of neural network layers	MVMTMDA [15]
	MMGCN [9]
	NMCMDA [36]
	GAEMDA [37]
	NIMCGCN [28]
The negative sampling ratio	MVMTMDA [15]
miRNA- and disease-related parameters
MiRNAs and diseases’ k nearest neighbours, whose similarity features were used to update the MDA adjacency matrix	MLPMDA [21]
	GRNMF [20]
Weights for constructing integrated similarity matrices of miRNAs and diseases	MLPMDA [21]
	AEMDA [17]
Parameter k of the KNN classifier for constructing the edges between the MDP nodes in the homogeneous graph	MDA–GCNFTG [32]

Type of parameters analyzed	Models performing the analysis
Matrix decomposition/completion-related parameters
The regularization coefficients in the objective function	MLPMDA [21]
	M2LFL [10]
	NIMCGCN [28]
	TDRC [30]
The dimensionality parameter for latent feature representation matrices of miRNAs and diseases	M2LFL [10]
	GRNMF [20]
	TDRC [30]
The number of computation layers for matrix decomposition/completion	MLPMDA [21]
The maximum number of iterations for optimizing the objective function	GRNMF [20]
Deep learning-related parameters
The regularization coefficients in the loss function	M2LFL [10]
The regularization coefficients in the loss function	GRNMF [20]
The size of miRNA and disease embeddings	AEMDA [17]
	MMGCN [9]
	GAEMDA [37]
The learning rate	MMGCN [9]
The number of filters in convolutional neural network	MMGCN [9]
The number of neural network layers	MVMTMDA [15]
	MMGCN [9]
	NMCMDA [36]
	GAEMDA [37]
	NIMCGCN [28]
The negative sampling ratio	MVMTMDA [15]
miRNA- and disease-related parameters
MiRNAs and diseases’ k nearest neighbours, whose similarity features were used to update the MDA adjacency matrix	MLPMDA [21]
	GRNMF [20]
Weights for constructing integrated similarity matrices of miRNAs and diseases	MLPMDA [21]
	AEMDA [17]
Parameter k of the KNN classifier for constructing the edges between the MDP nodes in the homogeneous graph	MDA–GCNFTG [32]

This Feature Is Available To Subscribers Only