Research Article
Differential Privacy for Evolving Network Based on GHRG
Algorithm 1
Dendrogram construction based on adjustment (DCBA).
| Input:sampled dendrogram at time t, evolving graphs , privacy parameter , . | | Output:sampled dendrogram at time t + 1. | (1) | if the result of change-point detection of is true then | (2) | Initialize the Markov chain by choosing a random starting dendrogram ; | (3) | for Markov chain step do | (4) | Randomly pick an internal node r in ; | (5) | Pick a neighboring dendrogram of by randomly drawing a configuration of r’s subtrees; | (6) | Accept the transition and set with probability ; | (7) | end for | (8) | if equilibrium is reached then | (9) | Return the sampled dendrogram ; | (10) | end if | (11) | else | (12) | for each new node do | (13) | for each internal node u whose child nodes are leaves in do | (14) | regard s as u’child node and construct a candidate set of the new dendrogram; | (15) | compute the log-likelihood of each candidate ; | (16) | end for | (17) | sample the new dendrogram with probability proportional to from the candidate set; | (18) | end for | (19) | Return the sampled dendrogram ; | (20) | end if |
|