Hongyuan You successfully passed his PhD proposal today on "Leveraging Network Information for Data-Driven Scientific Discovery"
Committee: Ambuj Singh (Chair), Yu-Xiang Wang, Sang-Yun Oh, Tommy Sprague
Network is a popular format for encoding structured information in applications ranging from spatial economics to neuroimaging studies. Discovering features of local processes and structures plays a key role in understanding and interpreting the overall state of complex networks. For example, absence or inhibition of interaction in the protein-protein network impacts the expression levels of protein pathways, which determines the presence or absence of disease; the existence of structural network fragments are significant for functional behavior in the neural system.
In this talk, I will first show that, though various regularization approaches, we can discover local substructures that affect global states or properties of network instances, or efficiently learn coherent models over networks that are robust to missing or corrupted edge weights. Second, I will discuss an ongoing project that models both the structure and function of brain connectivities, while we place hard network constraints driven by prior knowledge and model assumptions. In the end, I will discuss a future project of predicting fMRI responses via deep neural networks and a problem of integrating EEG, fMRI and DSI data.