Online Semi-Supervised Learning on Quantized Graphs

Michal Valko 1 Branislav Kveton 2 Huang Ling 3 Ting Daniel 4
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : In this paper, we tackle the problem of online semi-supervised learning (SSL). When data arrive in a stream, the dual problems of computation and data storage arise for any SSL method. We propose a fast approximate online SSL algorithm that solves for the harmonic solution on an approximate graph. We show, both empirically and theoretically, that good behavior can be achieved by collapsing nearby points into a set of local "representative points" that minimize distortion. Moreover, we regularize the harmonic solution to achieve better stability properties. We apply our algorithm to face recognition and optical character recognition applications to show that we can take advantage of the manifold structure to outperform the previous methods. Unlike previous heuristic approaches, we show that our method yields provable performance bounds.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-00642361
Contributor : Michal Valko <>
Submitted on : Friday, November 18, 2011 - 12:25:07 AM
Last modification on : Friday, June 28, 2019 - 4:34:05 PM
Long-term archiving on : Sunday, February 19, 2012 - 2:21:06 AM

File

valko2010online.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00642361, version 1

Collections

Citation

Michal Valko, Branislav Kveton, Huang Ling, Ting Daniel. Online Semi-Supervised Learning on Quantized Graphs. Uncertainty in Artificial Intelligence, Jun 2010, Catalina Island, United States. ⟨hal-00642361⟩

Share

Metrics

Record views

421

Files downloads

218