location_city Sydney schedule May 7th 03:40 - 04:10 PM place Red Room people 77 Interested

Geometric Deep Learning (GDL) is a fast developing machine learning specialisation that uses the network structure underlying the data to improve learning outcomes. GDL has been successfully applied to problems in various domains with network-structured data, such as social science, medicine, media, finance, etc.

Inspired by the success of neural networks in domains such as computer vision and natural language processing, the core component driving GDL is the graph convolution operator. This operator is used as the building block for deep learning models applied to networks. This approach takes advantage of many algorithmic and computational developments from modern neural network research and practice – such as composability, optimisation, and end-to-end training – to improve predictive performance.

However, there is a lack of tools for geometric deep learning targeting data scientists and machine learning practitioners.

In response, CSIRO’s Data61 has developed StellarGraph, an open source Python library. StellarGraph implements a number of state-of-the-art methods for GDL with a clean and consistent API. Furthermore, StellarGraph is designed to make the application of GDL algorithms to network-structured data easy to integrate with existing machine learning workflows.

In this talk, we will start with an overview of GDL and its real-world applications. Then we will introduce StellarGraph with a focus on its design philosophy, API and analytics workflow. Finally, we will demonstrate StellarGraph’s flexibility and ease-of-use for developing solutions targeting important applications such as product recommendation and social network moderation. Lastly, we will touch on the challenges of designing and implementing a library for a fast evolving machine learning field.


Outline/Structure of the Talk

  1. Geometric Deep Learning and its applications
    1. What is Geometric Deep Learning?
    2. Examples of real-world network-structured data
  2. From traditional machine learning to Geometric Deep Learning
    1. Representation learning on graphs
    2. Graph Convolutional Neural Networks
  3. The StellarGraph library:
    1. Geometric Deep Learning made easy
    2. API structure and design
    3. Basic workflow for geometric deep learning
  4. Examples:
    1. Movie recommendations
    2. Classifying Twitter hateful users

Learning Outcome

Participants will learn about the fast evolving machine learning specialisation of graph analytics and its real-world applications.

In addition, they will learn about the the open-source StellarGraph library and the data analysis workflow enabling fast and easy prototyping of solutions for graph-structured domains.

Target Audience

Data scientists, machine learning engineers/practitioners

Prerequisites for Attendees

Participants should have basic knowledge of Python, data science and/or machine learning, e.g., data preparation, feature engineering, regression and classification, deep learning, in an applied setting.



schedule Submitted 2 years ago