Fast link prediction for large networks using spectral embedding

2017/03/28 by Pachev, Benjamin, Webb, Benjamin · 2 citations
#FOS: Computer and information sciences #FOS: Physical sciences #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI)

paper · doi:10.48550/arxiv.1703.09693

Abstract

Many link prediction algorithms require the computation of a similarity metric on each vertex pair, which is quadratic in the number of vertices and infeasible for large networks. We develop a class of link prediction algorithms based on a spectral embedding and the k closest pairs algorithm that are scalable to very large networks. We compare the prediction accuracy and runtime of these methods to existing algorithms on several large link prediction tasks. Our methods achieve comparable accuracy to standard algorithms but are significantly faster.

Cited by

• Efficient Exact Resistance Distance Computation on Small-Treewidth Graphs: a Labelling Approach
• Katz similarity index comparisons

Related

• A Survey of Link Prediction Algorithms
• A Fast Parallel Approach for Neighborhood-based Link Prediction by Disregarding Large Hubs
• Link Prediction using Top-k Shortest Distances
• Pairwise Link Prediction
• Limitations and Alternatives for the Evaluation of Large-scale Link Prediction