On May 23, Kshiteesh Hegde defended a Ph.D. thesis on "Applications of Deep Network Signatures to Subgraph Classification, Quantification of Network Structure and Topologically Heterogeneous Node Classification," advised by Prof Malik Magdon-Ismail

On May 23, Kshiteesh Hegde defended a Computer Science Ph.D. thesis entitled "Applications of Deep Network Signatures to Subgraph Classification, Quantification of Network Structure and Topologically Heterogeneous Node Classification," supervised by NeST Professor Malik Magdon-Ismail. The thesis responses to the need for new tools and methods to effectively and efficiently make use of the vast information they contain. The thesis contributes novel techniques to (i) sample a large network such that downstream computations on the sparsified network produce results that are faithful to the full network (ii) extract network signatures and classify networks with high accuracy by transforming the problem of graph classification into one of image classification and using lossless image features, and simple machine learning algorithms to classify networks from a wide variety of domains with high accuracy, (iii) quantify network structure, by building on the success of the lossless image embedding feature to show that different networks have different intrinsic scales at which they exhibit peak structure, (iv) identify different behaviors occurring in different regions of topologically heterogeneous networks by building a lens that one can metaphorically hover on a heterogeneous network to discover different behaviors manifested by the network in different areas.