PyData Yerevan 2022

PyTorch Geometric for Graph Neural Nets
08-13, 14:30–15:10 (Asia/Yerevan), 114W PAB

  • In contrast to classical Deep Learning models (such as MLP, CNN, RNN, Transformers), which are usually applied to tensors and sequences, Graph Neural Net (GNN) is a special type of Deep Learning model, which works with non-euclidian data structures, such as graphs. Examples of graph analysis tasks, where a data-driven approach can help, may include 3D mesh processing, molecular analysis, social graphs data mining and potentially any other task, where traditional DL methods are inapplicable.
  • PyTorch is an industry standard Deep Leaning framework, which provides a lot of useful DL operations and utilities. PyTorch Geometric is a library built on top of PyTorch, implementing a set of tools to create and train Graph Neural Networks.
  • In this talk I will give a very quick and high-level introduction to GNNs and PyTorch Geometric.

  • Quick introduction to Geometric Deep Learning (GNNs, etc) and the applications
  • Quick introduction to PyTorch Geometric (main features, layers, etc)
  • A simple example of GNN implementation using PyTorch Geometric

Prior Knowledge Expected

Previous knowledge expected

Dmitry graduated with honors from Moscow State University with a M.Sc degree in Computer Science. His main research in the university was focused on computer vision and image processing within Graphics and Media Lab. After graduation Dmitry worked as a software engineer at IBM before moving to Samsung Electronics for 5 years where he undertook various research and development in areas of deep learning, computer vision and signal processing, as both an engineer and project manager. Currently he is a Director of Artificial Intelligence at NVIDIA, continuing research, development and team leading in these areas. From time to time he gives talks at conferences, conducts intensive seminars, courses, gives pop-science lectures and runs a Youtube channel on introduction to deep learning and related topics.