Fast link prediction for large networks using spectral embedding
From MaRDI portal
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.
Recommendations
- Link prediction in networks using effective transitions
- Sampling-based algorithm for link prediction in temporal networks
- Link prediction in scale-free networks using a partial observation
- Nonparametric link prediction in large scale dynamic networks
- Link prediction via sparse Gaussian graphical model
Cited in
(9)- Fast computation of Katz index for efficient processing of link prediction queries
- Algorithmic techniques for finding resistance distances on structured graphs
- Link prediction in networks using effective transitions
- Projection-based link prediction in a bipartite network
- A SOFT-LINK SPECTRAL MODEL FOR LINK PREDICTION
- LPmade: link prediction made easy
- Efficient Point-to-Point Resistance Distance Queries in Large Graphs
- High-Order Joint Embedding for Multi-Level Link Prediction
- Monotonicity of resistance distance in linear 2-trees
This page was built for publication: Fast link prediction for large networks using spectral embedding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3388881)
