Relative Entropy-Based Similarity for Patterns in Graph Data

Algorithm 1

Relative entropy-based similarity for patterns in graph data.

Input: A directed weighted graph data .

Output: Similarity matrix S of patterns in .

1: for each do

2: Calculate first-order neighbors

3: Calculate by equation (10)- (13)

4: end

5: for each with neighbors and with neighbors do

6: ifthen

7:  

8: else

9:  

10: end

11: end

12: fordo

13: Compute by equation (20) and (21)

14: Compute by equation (22)

15: end

16: for each do

17: Compute by equation (24)

18: Compute entropy matrix by equation (25)

19: Compute similarity matrix by equation (27)

20: end

21: return Similarity matrix S