Graph Neural Networks: Algorithm and Applications
YOW! Data 2018
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
Lead Data Scientist
Accomplished data science specialist with 10 years hands-on experience on data projects. Has been successful in developing machine learning approaches, which have proven advantage in various problem domains such as data mining, document categorisation, image & video recognition. High degree of expertise in deep artificial neural networks and graph modelling. Currently a data scientist working at SafetyCulture, leading development of innovative AI driven product features.