Skip to content

Latest commit

 

History

History
39 lines (24 loc) · 1.37 KB

README.md

File metadata and controls

39 lines (24 loc) · 1.37 KB
Raw

NoNCrossRank

This is an implementation of NoNCrossRank algorithm with Python.

The goal of this algorithm is to solve:
Given: (1) an Network of Networks (NoN) R = <G, A, θ>, and (2) the query vectors ei (i = 1, ..., g);
Find: ranking vectors ri for the nodes in the domain-specific networks Ai (i = 1, ..., g).

Functions

  • __init__.py: program entry;
  • CR_CrossValidation.py: cross rank cross validation;
  • CR_Precomputation.py: precompute the Anorm and Ynorm;
  • CR.py: ranking process;
  • J_CR.py: compute objective fuction;
  • AUCEvaluation.py AUC evaluation process;
  • AUCValue.py: compute AUC value;

Input/Output Format

- Input

G: the adjacency matrix of main network
A: domain specific networks A = (A1, ..., Ag)
θ: the one-to-one mapping function (mapping main node to domain-specific network)
ei: the query vector for Ai (i = 1, ..., g)

- Output

ri: the ranking vector for Ai (i = 1, ..., g)
AUCValue: the AUC value is used for evaluation

Reference

Ni, J., Tong, H., Fan, W., & Zhang, X. (2014, August). Inside the atoms: ranking on a network of networks. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 1356-1365). ACM.