Differentially Private Recommendation System Based on Community Detection in Social Network Applications
Description of symbols.
The modularity, evaluation index of community detection
, is the sum of the weights of all the links in the network
The weight between node and node
The sum of the weights of the edges attached from vertex
The sum of the weights of the links from to nodes in
The result of any query operation
is a random noise and follows the Laplace distribution of scale parameter
The sensitivity of
represents a given practical evaluation function. is data set, represents any legitimate output
is a social network. V represents the set of users in .. The friendship link denoted by . The set of user attributes is denoted by ..
The set of attribute categories in ,
The attribute value, equal to label,
The similarity of attributes between users
The accuracy of dependence
The parameters for evaluating utility, it is close to 1 that means utility better, otherwise, it is close to 0, utility lower
We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at email@example.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.