# Table 3 Distance functions considered in the paper.

Name Formulation
random distance $$D({v}_{i},{v}_{j})\sim N(\mu ,\sigma )$$
degree distance $$D({v}_{i},{v}_{j})=\frac{1}{{C}_{D}({v}_{j})+\varepsilon }$$
betweenness distance $$D({v}_{i},{v}_{j})=\frac{1}{{C}_{B}({v}_{j})+\varepsilon }$$
closeness distance $$D({v}_{i},{v}_{j})=\frac{1}{{C}_{C}({v}_{j})+\varepsilon }$$
page rank distance $$D({v}_{i},{v}_{j})=\frac{1}{{C}_{P}({v}_{j})+\varepsilon }$$
euclidean 1-D distance $$D({v}_{i},{v}_{j})=|{a}_{i}^{1}-{a}_{j}^{1}|$$
euclidean 2-D distance $$D({v}_{i},{v}_{j})=\sqrt{{({a}_{i}^{1}-{a}_{j}^{1})}^{2}+{({a}_{i}^{2}-{a}_{j}^{2})}^{2}}$$
cosine distance $$D({v}_{i},{v}_{j})=1-\frac{{v}_{i}\circ {v}_{j}}{\parallel {v}_{i}\parallel \cdot \parallel {v}_{j}\parallel }$$
aggregate distance $$D({v}_{i},{v}_{j})=\sum _{k=1}^{m}\,{w}_{k}D({a}_{i}^{k},{a}_{j}^{k})$$
linear regression distance $$D({v}_{i},{v}_{j})={W}_{ij}\beta$$, $${W}_{ij}=({a}_{i}^{1},\ldots ,{a}_{i}^{p},{a}_{j}^{1},\ldots ,{a}_{j}^{p},\varepsilon )$$
naive bayes classifier distance $$D({v}_{i},{v}_{j})=\frac{P(C=1|{W}_{ij})}{P(C=0|{W}_{ij})+\varepsilon }$$