Predictive and Generative Deep Learning for Graphs
Graphs are a natural way to model many real-world complex objects. In this talk, after a brief review of recent advances in using deep learning for graphs, we will present our approach to create inference models based on novel attention mechanisms for graph convolutional neural networks making them robust to noise with added interpretability. We will show their applications to very large semi-automatically generated biological networks. In addition, we will discuss our recent approaches to model and generate graphs with optimal properties using RL as well as an architecture for conditional generative graph models which are applied to create novel chemical compounds.
Amir Saffari has a PhD in Machine Learning and has been working in the field of Artificial Intelligence for more than 15 years, researching and developing ML based theory, applications, and, products. He’s numerous publications in top-tier ML conferences and journals and most of his research has been released as open source software. He was part of Sony’s R&D team and has been involved in a few ML startups.