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

  • Assemblée générale des membres du CRIM - 18 juin 2020
    18 June 2020 0:00
    CRIM (405, avenue Ogilvy, bureau 101, Montréal)
    Les membres du CRIM sont convoqués à l'Assemblée générale annuelle qui se tiendra le 18 juin 2020. Ne manquez pas cette importante réunion et l'occasion de vous tenir au fait de plusieurs dossiers qui vous concernent.
  • Prompt RT @Prompt_Innov: [ WEXPERT ?La Ville intelligente Nos intervenants : Philippe Beaudoin, co-fondateur d’ @element_ai Stéphane Barbier, di…
  • CEIM RT @CEIM_Qc: Bonne nouvelle! Le gala de l' @ADRIQ_RCTi aura bien lieu, que ce soit en présentiel ou en virtuel! Ne passez pas à côté de cet…