Graph ML

Graph Machine Learning is the science between graph theory and machine learning. It is now a very active area of research, with hundreds of publications each month, impactful applications in the industry, and new insights about our world. Intersection of graph theory and machine learning. Overview, SOTA, applications.

At Data Fest 2020 in our section we will have 10 speakers, loosely divided into 2 subtracks: research and industry. At the research subtrack you can hear about recent advancements in graph machine learning such as nearest neighbor search and graph embeddings. At the industry subtract speakers will talk about different applications in this area such as graph visualization or link prediction in the bank industry. 

What you should expect from our track? 

Our track has 10 videos. Each video is between 10 and 30 minutes. You can watch videos at your own pace.


  • Graph-Based Nearest Neighbor Search: Practice and Theory (Liudmila Prokhorenkova)
  • Unsupervised Graph Representations (Anton Tsistulin)
  • Placing Knowledge Graphs in Graph ML (Michael Galkin)
  • Graphical Models for Tensor Networks and Machine Learning (Roman Schutski)
  • Scene Graphs from the Graph Neural Networks Perspective (Boris Knyazev)
  • Business Transformation through the Problems on Graphs (Vadim Safronov)
  • Large Graph Visualization Tools and Approaches (Sviatoslav Kovalev)
  • AutoGraph: Graphs Meet AutoML (Denis Vorotinsev)
  • Link Prediction with Graph Neural Networks (Maxim Panov)

Track program