Colloquium - Machine Learning on Graphs

April 19, 2019 - 4:00pm
118 MLH
Bryan Perozzi

Machine Learning on Graphs (also known as Relational Learning, or Graph-Based Machine Learning) is a branch of ML which focuses on problems where the data items (nodes) contain discrete relationships (edges) between themselves (usually in addition to traditional real-valued feature vectors). The structure of these links between unlabelled data items can be leveraged for both semi-supervised learning and unsupervised learning algorithms.

In this talk, I will provide an overview of the area, and some recent results from our team in clustering and representation learning. When appropriate, I will try to motivate our research with examples of real world problems.



 Bryan Perozzi - Google staff picBryan Perozzi is a Senior Research Scientist in Google AI’s Algorithms and Optimization group, where he routinely analyzes some of the world’s largest (and perhaps most interesting) graphs. Bryan’s research focuses on developing techniques for learning expressive representations of relational data with neural networks. These scalable algorithms are useful for prediction tasks (classification/regression), pattern discovery, and anomaly detection in large networked data sets.

Bryan is an author of 20+ peer-reviewed papers at leading conferences in machine learning and data mining (such as NeurIPS, KDD, and WWW). His doctoral work on learning network representations was awarded the prestigious KDD Dissertation Award.  Bryan received his Ph.D. in Computer Science from Stony Brook University in 2016, and his M.S. from the Johns Hopkins University in 2011.