Leveraging the Structure of Data
(July 5, 1:00 PM - 2:00 PM)
Bryan's research at Stony Brook focused on applying representation learning (or deep learning) to applications in social network analysis (including link prediction, user-profiling, etc.) and natural language processing. Bryan won an IACS Junior Researcher Award for 2 years, was the recipient of the Catacosinos Fellowship for Excellence in Computer Science, and received the Best Paper (runner-up) award at the SIAM Conference on Data Mining in 2016 for his work on anomaly detection in graphs. He was advised by Professor Steven Skiena. Bryan is a Research Scientist on the Graph Mining team at Google. For more information about research at Google, see ""Google's Hybrid Approach to Research"" or website."
Although predictions from machine learning models influence more and more of our lives, the standard way of posing a ML problem has remained relatively unchanged for decades. In the search for better models, a new and popular family of techniques (sometimes called Graph Machine Learning) has emerged. These techniques rely on expanding beyond the features of an individual entity and instead look to pull information from its relationships. The methods offer a tantalizing way of improving task performance by leveraging previously unused information. However, it is not a free lunch, as these models can be more complex, difficult to train, and may have challenges in interpretability. This talk will discuss the fundamentals of graph machine learning, a few models, and some insights from years of real-world applications.