CRIM Blog - Deep learning applied to graphs

CRIM Blog - Deep learning applied to graphs

Published October 16, 2018


Extraction and processing of graph information by convolutional neural networks

by Jade Guisiano, data science intern at CRIM
Originally published on Medium


Graphs — frequently used in the fields of transport, telecommunication, biology, sociology and others — allow, in the simplest cases, an exploration of data and their connectivity from a simple visual analysis. However, in most applications, for example in the classic case of the representation of social networks, the graphs obtained contain an immense quantity of nodes and connexions between them. When that’s the case, simple visual analyzes can quickly become complex. The use of machine learning on massive data graphs is a solution for numerous analytical and predictive approaches such as clustering for community detection, social link inference, vertex classification without a label, etc.

Deep learning is inspired by the functioning and architecture of brain systems: it uses artificial neural networks capable of solving complex problems with training. Deep learning seeks to learn through an algorithm composed of various layers of artificial neurons. The higher the number, the more the algorithm can handle with complex problems. In the context of large data volume processing, the use of deep learning and more specifically convolutional neural networks seems to be appropriate. Indeed, unlike multilayer perceptrons, convolutional neural networks limit the number of connections between neurons from one layer to another, which has the advantage of reducing the number of parameters to be learned.

Recent research is concerned with the application of convolutional neural networks to graphs. Convolutional neural networks are generally used for processing data defined in a Euclidean space (finite dimensional vector space) such as images structured on a regular grid formed by ordered pixels. However, graphs have no set structure or order allowing them to be processed in this way by convolutional neural networks.

A recent method called “Deep Graph Convolutional Neural Network” (DGCNN) proposed by M.Zhang et al. (2018) [1] exposes a new architecture of convolutional neural networks for graph processing.

Read the complete article on Medium

Upcoming event

  • Carrefour carrières collège Stanislas de Montréal
    18 November 2019 12:30
    Collège Stanislas de Montréal
    Lise Rebout, Spécialiste en traitement automatique des langues naturelles au CRIM, présentera son parcours lors du Carrefour carrières collège Stanislas de Montréal le 18 novembre 2019.
  • #Bientôt ???? Le CRIM présentera le projet Application des technologies vocales aux langues autochtones le 19 novembre…
  • Tom Landry RT @Tom_Landry_: Ce fût un réel plaisir que de partager ma vision de l'avenir de la géomatique. Et que dire des mots-clés sélectionné par l…