Using Graph CNNs in Keras

  • V_1 is a Netflix user who watched “House of Cards” and rated it with 5 stars.
  • V_2 is “House of Cards
  • V_3 is another Netflix user who is befriended with V_1
  • We label V_1 as a “House of Cards” lover, encoded by the label 1
  • We label the Series V_2 as 2
  • and we want to guess the label for V_3.
  1. x_1 = most liked genre
  1. x_1 = genre

Verma’s Graph Learning Implementation

  • If we set the filter to the identity matrix, we have a usual MLP, without the edge relations.
  • If we set it to A, we are using the edge information in the most basic way.
  • If we set it to concat[A, A*A^t] we are using the edges as well as putting special attention on large weights. This would be two filters, not one anymore btw.

Examples on More Data

Example 1, a Simple MLP

Example 3, two Filters

Resources

--

--

--

Ph.D., Product Manager, DevOps & Data enthusiast, and author of “Three Data Point Thursday” & http://datacisions.com

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

3. Monte Carlo Methods

Building up your career with ML (ScholarX write up — Part1)

Guide to the NIPS 2018 competition track and how you can participate

Different types of distance used in Machine Learning.

Fine Grained Image Classification using Bilinear Convolutional Neural Networks - Tensorflow V2

Data extraction using DML

Confronting the risk of using Machine Learning — What banks need to do?

Introducing PFRL: A PyTorch-based Deep RL library

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Sven Balnojan

Sven Balnojan

Ph.D., Product Manager, DevOps & Data enthusiast, and author of “Three Data Point Thursday” & http://datacisions.com

More from Medium

Synthetic Data Generation

Graph Databases and Object Graph Mapping with neo4j and python

How a pretrained TabTransformer performs in the real world