Fast distributed k-nn graph update

Thibault Debatty (1, 2) , Fabio Pulvirenti (2) , Pietro Michiardi (2) , Wim Mees (1)

1 Ecole Royale Militaire
2 Eurecom [Sophia Antipolis]

In this paper, we present an approximate algorithm that is able to quickly modify a large distributed k-nn graph by adding or removing nodes. The algorithm produces an approximate graph that is highly similar to the graph computed using a naïve approach, although it requires the computation of far fewer similarities. To achieve this goal, it relies on a novel, distributed graph based search procedure. All these algorithms are also experimentally evaluated, using both euclidean and non-euclidean datasets.

Domaines: Algorithme et structure de données [cs.DS]; Intelligence artificielle [cs.AI]

Thibault Debatty, Fabio Pulvirenti, Pietro Michiardi, Wim Mees. Fast distributed k-nn graph update. 2016 IEEE International Conference on Big Data, Dec 2016, Washington, DC, United States. pp.3308-3317, ⟨10.1109/BigData.2016.7840990⟩. ⟨hal-01525697⟩