Graph Neural Networks: Algorithm and Applications

schedule May 14th 03:55 - 04:25 PM place Wesley Theatre people 214 Interested

Artificial neural networks help us cluster and classify. Since "Deep learning" became the buzzword, it has been applied for many advances of AI, such as self-driving car, image classification, Alpha Go, etc. There are lots of different deep learning architectures, the most popular ones are based on the well known convolutional neural network which is one type of feed-forward neural networks. This talk will introduce another variant of deep neural network - Graph Neural network which can model the data represented as generic graphs (a graph can have labelled nodes connected via weighted edges). The talk will cover:

  • the graph (graph of graphs - GoGs) representation: how we represent different data with graphs
  • architecture of graph neural networks (GNN): the architecture of deep graph neural networks and learning algorithm
  • applications of GoGs and GNNs: document classification, web spam detection, human action recognition in video

1 favorite thumb_down thumb_up 1 comment visibility_off  Remove from Watchlist visibility  Add to Watchlist

Outline/Structure of the Talk

  • Introduction and Background of Deep Learning
  • Graph and Graph of graphs (GoG) data representation: why and how
  • Supervised learning model: Graph Neural Networks (GNN) architecture + algorithm
  • Applications of GoGs and GNNs - Web Page Spam Detection
  • Applications of GoGs and GNNs - Human Action Recognition from unconstrained videos
  • Conclusion and Discussion

Learning Outcome

  • Powerful data representation with graphs
  • A deep learning architecture different from CNN which can be applied for many problem domains

Target Audience

interested in deep neural networks

schedule Submitted 1 year ago

Public Feedback

comment Suggest improvements to the Speaker
  • Josh Graham
    By Josh Graham  ~  11 months ago
    reply Reply

    Hi Shujia,

    We're liking this a lot. When you present, can you make sure it's not simply tutorial. You can include pros/cons and experiences of when these have been a superior approach or a mistake.

    See you there!