Mark Heimann

Mark Heimann

I am a PhD candidate in the computer science department at the University of Michigan, where I consider myself fortunate to be a member of the GEMS Lab and advised by Danai Koutra. I am spending the summer of 2019 at the Information Sciences Institute in California working with Emilio Ferrara using node embeddings to detect cyberbullying in social media at the level of individual users as well as media sessions. Previously, I spent Winter 2019 interning remotely with Ryan Rossi at Adobe Research working on entity resolution, and in the summer of 2018 I was at Oak Ridge National Laboratory, working with Ramakrishnan Kannan on nonlinear dimensionality reduction. We collaborated with researchers at the Center for Nanophase Materials Sciences to develop new algorithms for hyperspectral unmixing.

My current research focuses on representation learning in networks, where I am developing methods for node embedding that preserve the similarity between nodes with similar structural roles in a network or networks. Such node embeddings are comparable even across entirely different networks, for example when performing multi-network tasks such as network alignment or classification. I have broader interests in methods and applications for representation learning, matrix factorization, and nonlinear dimensionality reduction.

Publications

*Equal contribution