Mark Heimann

Academic Activities

Tutorials

Mark Heimann, Junchen Jin, and Danai Koutra. Network Embedding for Role Discovery: Concepts, Tools, and Applications. SDM 2022.
Konstantia Georgouli, Mark Heimann, Harsh Bhatia, Timothy S. Carpenter, Felice C. Lightstone, Helgi I. Ingólfsson, Peer-Timo Bremer. "Generating Protein Structures for Pathway Discovery Using Deep Learning." AAAI Symposium on Computational Approaches to Scientific Discovery. March 2023.

Guest lecture, Department of Computer Science, Vanderbilt University. "Embedding-based Role Discovery." Nashville, TN (virtual). December 2021.
Invited presentation, SPIRAL Seminar, Northeastern University. "Refining Network Alignment to Achieve Matched Neighborhood Consistency." Boston, MA (virtual). April 2021.
Guest lecture, Department of Information Systems, Carnegie Mellon University. "Introduction to Machine Learning." Pittsburgh, PA (virtual). October 2020.
5th International Summer School on Data Science. "Node Embedding on Multiple Networks." Split, Croatia (virtual). September 2020.
NABD Conference, Criteo Labs. "REGAL: Representation Learning-based Graph Alignment." Ann Arbor, MI, USA. May 2019.
Center for Nanophase Materials Science User Meeting, Oak Ridge National Laboratory. "Machine Learning in Materials Science: An Introduction through Python." Oak Ridge, TN, USA. August 2018.

Instructor: Mining and Learning with Graphs (Lawrence Livermore National Laboratory, short course for Data Science Summer Institute, Summer 2022)
Graduate Course TA: EECS 592, Introduction to Artificial Intelligence (UMich, Winter 2017); CSE 516A, Multi-Agent Systems (WUSTL, Spring 2015)
Undergraduate Course TA: CSE 417A, Introduction to Machine Learning (WUSTL, Fall 2014); CSE/Pol Sci 245A, Fair Division in Theory and Practice (WUSTL, Spring 2015); EECS 376, Foundations of Computer Science (UMich, Fall 2016/2017)