Harlin Lee

Bio: Harlin Lee is a Hedrick Assistant Adjunct Professor at UCLA Mathematics. She received her PhD in Electrical and Computer Engineering at Carnegie Mellon University in 2021. She also has a MS in Machine Learning from Carnegie Mellon University, and a BS + MEng in Electrical Engineering and Computer Science from MIT. Her research is on learning from high-dimensional data supported on structures such as graphs (networks), low-dimensional subspace, or sparsity, motivated by applications in healthcare and social science. Harlin’s lifelong vision is to use data theory to help everyone live physically, mentally and socially healthier.

Talk Title: Understanding scientific fields via network analysis and topic modeling

Talk Abstract: As scientific disciplines get larger and more complex, it becomes impossible for an individual researcher to be familiar with the entire body of literature. This forces them to specialize in a sub-field, and unfortunately such insulation can hinder the birth of ideas that arise from new connections, eventually slowing down scientific progress. As such, discovering fruitful interdisciplinary connections by analyzing scientific publications is an important problem in the science of science. This talk will present several past and ongoing projects towards answering that question using tools from network analysis and topic modeling: 1) a dynamic-embedding-based method for link prediction in a machine learning/AI semantic network, 2) finding communities in cognitive science that study similar topics but do not cite each other or publish in the same venues, and 3) developing theoretically grounded hypergraph embedding methods to capture surprising collaborations or missed opportunities.