You are cordially invited to attend the PhD defense of Olivier Ruas that will be held December 17 at 10am, Room Petri-Turing and for a drink in Room Markov.
Jury members:
Sara Bouchenak, Professor, Insa Lyon
Antonio Fernandez Anta, Research Professor, IMDEA Networks Institute
Marc Tomasi, Professor, Université de Lille 3
Anne-Marie Kermarrec, CEO, Mediego
David Gross-Amblard, Professor, Université de Rennes 1
François Taiani, Professor, Université de Rennes 1
Title: The many faces of approximation in KNN graph computing
Abstract:
The incredible quantity of available content in online services makes content of interest incredibly difficult to find. The most emblematic way to help the users is to do item recommendation. The K-Nearest-Neighbors (KNN) graph connects each user to its k most similar other users, according to a given similarity metric. The computation time of an exact KNN graph is prohibitive in online services. Existing approaches approximate the set of candidates for each user’s neighborhood to decrease the computation time. In this thesis we push farther the notion of approximation : we approximate the data of each user, the similarity and the data locality. The resulting approach clearly outperforms all the other ones.
