Table 3: Computational time complexity and bibliographic references for the link scoring and prediction methods provided by NOESIS.


LocalCommon neighbors count[59]
Adamic–Adar score[60]
Resource-allocation index[61]
Adaptive degree penalization score[62]
Jaccard score[63]
Leicht–Holme–Newman score[64]
Salton score[65]
Sorensen score[66]
Hub promoted index[67]
Hub depressed index[67]
Preferential attachment score[68]

GlobalKatz index[34]
Leicht–Holme–Newman score[64]
Random walk[69]
Random walk with restart[70]
Flow propagation[71]
Pseudoinverse Laplacian score[72]
Average commute time score[72]
Random forest kernel index[73]

In the time complexity analysis, is the number of nodes in the network, d is the maximum node degree, and c refers to the number of iterations required by iterative global link prediction methods.