A Metric Learning Approach for Graph-Based Label Propagation

Pauline Wauquier 1, 2 Mikaela Keller 1, 3
1 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : The efficiency of graph-based semi-supervised algorithms depends on the graph of instances on which they are applied. The instances are often in a vectorial form before a graph linking them is built. The construction of the graph relies on a metric over the vectorial space that help define the weight of the connection between entities. The classic choice for this metric is usually a distance measure or a similarity measure based on the euclidean norm. We claim that in some cases the euclidean norm on the initial vectorial space might not be the more appropriate to solve the task efficiently. We propose an algorithm that aims at learning the most appropriate vectorial representation for building a graph on which the task at hand is solved efficiently.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01427287
Contributor : Team Magnet <>
Submitted on : Thursday, January 5, 2017 - 3:35:46 PM
Last modification on : Friday, March 22, 2019 - 1:35:35 AM
Long-term archiving on : Thursday, April 6, 2017 - 1:56:18 PM

File

wauquier_keller.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01427287, version 1

Citation

Pauline Wauquier, Mikaela Keller. A Metric Learning Approach for Graph-Based Label Propagation. Workshop track of ICLR 2016, May 2016, San Juan, Puerto Rico. ⟨hal-01427287⟩

Share

Metrics

Record views

260

Files downloads

128