Title :
Fast decentralized learning of a Gaussian mixture model for large-scale multimedia retrieval
Author :
Nikseresht, A. ; Gelgon, M.
Author_Institution :
Lab. d´´Informatique Nantes-Atlantique, Ecole polytechnique de l´´universite de Nantes, France
Abstract :
We address herein the distributed computation of a probability density estimate. Class-conditional probability density estimation is a central need in multimedia pattern recognition, but has classically be conducted in a centralized fashion. In contrast, the present work is motivated by the perspective of a multimedia indexing and retrieval peer-to-peer system over the Internet. In a decentralized fashion, algorithms and data from various contributors would cooperate towards a collective statistical learning. A typical need is aggregation of probabilistic Gaussian mixture models describing the same class, but estimated on several nodes on different data sets. We tackle this goal through an approach requiring only moderate computation at each node and little data to transit between nodes. Both properties are obtained by fusion models via their (few) parameters, rather than via multimedia data itself. Estimation of the aggregated model is provided by an iterative scheme, derived from a modification on Kullback divergence. We provide experimental results on a speaker recognition task with real data, in a gossip propagation setting.
Keywords :
Gaussian processes; Internet; indexing; information retrieval; multimedia systems; pattern recognition; peer-to-peer computing; Gaussian mixture model; Internet; Kullback divergence; class-conditional probability density estimation; collective statistical learning; distributed computation; fast decentralized learning; gossip propagation; large-scale multimedia retrieval; multimedia indexing; multimedia pattern recognition; peer-to-peer system; probabilistic Gaussian mixture models; probability density estimate; speaker recognition; Distributed computing; Indexing; Large-scale systems; Multimedia systems; Pattern recognition; Peer to peer computing; Speaker recognition; Supervised learning; Training data; Web pages;
Conference_Titel :
Parallel, Distributed, and Network-Based Processing, 2006. PDP 2006. 14th Euromicro International Conference on
Print_ISBN :
0-7695-2513-X
DOI :
10.1109/PDP.2006.37