Scaling KNN computation over large graphs on a PC
Nitin Chiluka, Anne-Marie Kermarrec, Javier Olivares · 2014
This paper proposes a novel approach to compute K-Nearest Neighbors (KNN) algorithm on a large set of users by leveraging disk and memory efficiently on a commodity PC. The system is designed to minimize random accesses to disk as well as the amount of data loaded/unloaded from/to disk so as to better utilize the computational power, thus improving the algorithmic efficiency.