Research Scientist, Data Mining & Machine Learning
I develop techniques for learning expressive representations of social relationships and natural language with neural networks. These scalable algorithms are useful for prediction tasks (classification/regression), pattern discovery, and anomaly detection in large networked data sets. I have 20+ peer-reviewed papers, and my work has been featured at the leading conferences in machine learning (NeurIPS, ICML), data mining (KDD), and information retrieval (WWW). In addition to my academic background, I also have 6+ years of full time industry experience building large-scale data analytic systems. (I was doing data science before it was cool.)
Talks and Events
2022 Talk: Challenges Of Applying Graph Neural Networks
Graph Neural Networks are a tantalizing way of modeling data which doesn’t have a fixed structure. However, getting them to work as expected has had some twists and turns over the years. In this talk, I’ll describe the Graph Mining team’s work at Google to make GNNs useful. I’ll focus on challenges that we’ve identified and the solutions we’ve developed for them. Specifically, I’ll be highlighting work that’s led to more expressive graph convolutions, more robust models, and better graph structure.