Dr. Sutanay Choudhury (PI) is a Chief Scientist at PNNL with 10+ years of experience in large-scale graph analytics and machine-learning. His research focuses on learning high-fidelity representations of structure from complex data sources and development of methods for reasoning and prediction on such representations. Dr. Choudhury serves as a research thrust lead for PNNL's internal initiative on AI research. He has served as PI, Co-PI and contributor on multiple projects funded by the DoD, DHS, DOE and PNNL’s internal research programs developing multiple systems focusing on graph analytics and graph neural networks. He developed StreamWorks, a streaming graph analytics system that received R&D100 award for novel applications in cyber-security.
Many important application data streams can be modeled as a complex graph of entities, where each graph node or entity is associated with a multi-variate time-series. The overall system’s behavior is modeled as a dynamical system, and it evolves through structural changes in the graph, and/or...