Fractional Graph-based Semi-Supervised Learning

Sarah De Nigris 1 Esteban Bautista 1 Patrice Abry 2 Konstantin Avrachenkov 3 Paulo Gonçalves 1
1 DANTE - Dynamic Networks : Temporal and Structural Capture Approach
Inria Grenoble - Rhône-Alpes, LIP - Laboratoire de l'Informatique du Parallélisme, IXXI - Institut Rhône-Alpin des systèmes complexes
3 NEO - Network Engineering and Operations
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Graph-based semi-supervised learning for classifica- tion endorses a nice interpretation in terms of diffusive random walks, where the regularisation factor in the original optimisation formulation plays the role of a restarting probability. Recently, a new type of biased random walks for characterising certain dynamics on networks have been defined and rely on the γ- th power of the standard Laplacian matrix Lγ, with γ > 0. In particular, these processes embed long range transitions, the Le ́vy flights, that are capable of one-step jumps between far- distant states (nodes) of the graph. The present contribution envisions to build upon these volatile random walks to propose a new version of graph based semi-supervised learning algorithms whose classification outcome could benefit from the dynamics induced by the fractional transition matrix
Type de document :
Communication dans un congrès
EUSIPCO 2017 - 25th European Signal Processing Conference, Aug 2017, Kos Island, Greece
Liste complète des métadonnées
Contributeur : Paulo Gonçalves <>
Soumis le : mercredi 13 septembre 2017 - 11:32:17
Dernière modification le : jeudi 1 novembre 2018 - 01:21:17


  • HAL Id : hal-01586767, version 1


Sarah De Nigris, Esteban Bautista, Patrice Abry, Konstantin Avrachenkov, Paulo Gonçalves. Fractional Graph-based Semi-Supervised Learning. EUSIPCO 2017 - 25th European Signal Processing Conference, Aug 2017, Kos Island, Greece. 〈hal-01586767〉



Consultations de la notice