Research

I am a research scientist at Ivo, where since August 2026 I have worked on supervised fine-tuning, prompt optimization, and post-training methods for knowledge-intensive domains such as law. Before that, I was a senior research scientist in the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory. In 2020, I received my PhD in computer science from the University of Michigan, where I was a member of the GEMS Lab and advised by Danai Koutra. During my PhD I also completed internships at the Information Sciences Institute, Adobe Research and Oak Ridge National Laboratory. I completed my undergraduate degree at Washington University in St. Louis in 2015.

My research is in machine learning for graph or network-structured data. You can read more about my PhD work using node and graph level embeddings in technical detail in my dissertation, or more quickly consult a conceptual confectionary conspectus in the dessertation I made to celebrate my dissertation defense. At Lawrence Livermore National Laboratory, I worked on new graph neural network methods and applications to molecular modeling, scientific image segmentation, and software analysis, and later on foundation models and their applications to problems in bioinformatics.

Google Scholar Resume (PDF) GitHub

Selected publications

A short list to start with. The full list follows.

ICLR 2024

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Trivedi, Heimann, Anirudh, Koutra, Thiagarajan
NeurIPS 2022

Understanding Self-Supervised Graph Representation Learning from a Data-Centric Perspective
Trivedi, Lubana, Heimann, Koutra, Thiagarajan
NeurIPS 2020

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Zhu, Yan, Zhao, Heimann, Akoglu, Koutra
ICDM 2019

Distribution of Node Embeddings as Multiresolution Features for Graphs
Heimann, Safavi, Koutra
Best Student Paper

All publications

* marks equal contribution.

2025

SDM

Conformal Edge-Weight Prediction in Latent Space
Akash Choudhuri, Yongjian Zhong, Mehrdad Moharrami, Christine Klymko, Mark Heimann, Jayaraman J. Thiagarajan, Bijaya Adhikari

2024

Journal of Chemical Theory and Computation

Generating Protein Structures for Pathway Discovery Using Deep Learning
Konstantia Georgouli, Robert Stephany, Jeremy Tempkin, Claudio Santiago, Fikret Aydin, Mark Heimann, Loïc Pottier, Xiaohua Zhang, Timothy Carpenter, Tim Hsu, Dwight Nissley, Frederick Streitz, Felice Lightstone, Helgi Ingólfsson, Peer-Timo Bremer
BioKDD @ KDD

Adapting Large Language Models to Predict Gene Interactions
Mark Heimann, Christine Klymko, Jayaraman J. Thiagarajan
ICLR

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra, Jayaraman J. Thiagarajan

Also presented at DMLR @ ICML 2023 and GLFrontiers @ NeurIPS 2023.

2023

LoG

On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
Donald Loveland, Jiong Zhu, Mark Heimann, Benjamin Fish, Michael T. Schaub, Danai Koutra
IEEE Data Engineering Bulletin

Heterophily and Graph Neural Networks: Past, Present, and Future
Jiong Zhu, Yujun Yan, Mark Heimann, Lingxiao Zhao, Leman Akoglu, Danai Koutra
ICIP

Modeling Hierarchical Topological Structure in Scientific Images with Graph Neural Networks
Samuel Leventhal, Attila Gyulassy, Valerio Pascucci, Mark Heimann

Also accepted at GLFrontiers @ NeurIPS 2022.
TVCG

Exploring Classification of Topological Priors with Machine Learning for Feature Extraction
Samuel Leventhal, Attila Gyulassy, Mark Heimann, Valerio Pascucci
WACV

Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification
Rakshith Subramanyam, Mark Heimann, Jayram Thathachar, Rushil Anirudh, Jayaraman J. Thiagarajan

2022

NeurIPS

Understanding Self-Supervised Graph Representation Learning from a Data-Centric Perspective
Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, Jayaraman J. Thiagarajan

Also accepted at GLB @ WebConf 2022 and MLG @ KDD 2022.
CIKM

CAPER: Coarsen, Align, Project, Refine – A General Multilevel Framework for Network Alignment
Jing Zhu, Danai Koutra, Mark Heimann
DLG @ KDD

On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods
Donald Loveland, Jiong Zhu, Mark Heimann, Ben Fish, Michael T. Schaub, Danai Koutra
CompBio @ ICML

Emerging Patterns in the Continuum Representation of Protein-Lipid Fingerprints
Konstantia Georgouli, Helgi I. Ingólfsson, Fikret Aydin, Mark Heimann, Felice Lightstone, Peer-Timo Bremer, Harsh Bhatia

2021

SDM

Refining Network Alignment to Improve Matched Neighborhood Consistency
Mark Heimann, Xiyuan Chen, Fatemeh Vahedian, Danai Koutra

Code
SDM

Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding
Jing Zhu*, Xingyu Lu*, Mark Heimann, Danai Koutra

Code
TKDD

Towards Understanding and Evaluating Structural Node Embedding
Junchen Jin, Mark Heimann, Di Jin, Danai Koutra

Also invited for a contributed talk at MLG @ KDD 2020.

Code Video

2020

NeurIPS

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra

Code
Complex Networks

Structural Node Embedding in Signed Social Networks: Finding Online Misbehavior at Multiple Scales
Mark Heimann, Goran Murić, Emilio Ferrara

Code
CIKM

CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding
Xiyuan Chen, Mark Heimann, Fatemeh Vahedian, Danai Koutra

Also accepted at MLG @ KDD 2020.

Code Video
CIKM

G-CREWE: Graph CompREssion With Embedding for Network Alignment
Kai Qin, Flora D. Salim, Yongli Ren, Wei Shao, Mark Heimann, Danai Koutra

Code

2019

ICDM

Distribution of Node Embeddings as Multiresolution Features for Graphs
Mark Heimann, Tara Safavi, Danai Koutra

Code
Best Student Paper
ECML PKDD

node2bits: Compact Time- and Attribute-aware Node Representations for User Stitching
Di Jin, Mark Heimann, Ryan Rossi, Danai Koutra

Code
KDD

Smart Roles: Inferring Professional Roles in Email Networks
Di Jin*, Mark Heimann*, Tara Safavi, Mengdi Wang, Wei Lee, Lindsay Snider, Danai Koutra

Code

2018

CIKM

REGAL: Representation Learning-based Graph Alignment
Mark Heimann, Haoming Shen, Tara Safavi, Danai Koutra

Code
PAKDD

HashAlign: Hash-Based Alignment of Multiple Graphs
Mark Heimann*, Wei Lee*, Shengjie Pan, Kuan-Yu Chen, Danai Koutra

Code
SDM

Fast Flow-based Random Walk with Restart in a Multi-query Setting
Yujun Yan, Mark Heimann, Di Jin, Danai Koutra

Code

2017

MLG @ KDD

On Generalizing Neural Node Embedding Methods to Multi-Network Problems
Mark Heimann, Danai Koutra

Tutorials and talks

Tutorials and symposia

March 2023

Generating Protein Structures for Pathway Discovery Using Deep Learning
AAAI Symposium on Computational Approaches to Scientific Discovery

Konstantia Georgouli, Mark Heimann, Harsh Bhatia, Timothy S. Carpenter, Felice C. Lightstone, Helgi I. Ingólfsson, Peer-Timo Bremer
2022

Network Embedding for Role Discovery: Concepts, Tools, and Applications
SDM

Mark Heimann, Junchen Jin, Danai Koutra

Invited talks

December 2021

Embedding-based Role Discovery
Guest lecture, Department of Computer Science, Vanderbilt University. Nashville, TN (virtual).
April 2021

Refining Network Alignment to Achieve Matched Neighborhood Consistency
Invited presentation, SPIRAL Seminar, Northeastern University. Boston, MA (virtual).
October 2020

Introduction to Machine Learning
Guest lecture, Department of Information Systems, Carnegie Mellon University. Pittsburgh, PA (virtual).
September 2020

Node Embedding on Multiple Networks
Lecture, 5th International Summer School on Data Science. Split, Croatia (virtual).
May 2019

REGAL: Representation Learning-based Graph Alignment
Talk, NABD Conference, Criteo Labs. Ann Arbor, MI.
August 2018

Machine Learning in Materials Science: An Introduction through Python
Talk, Center for Nanophase Materials Science User Meeting, Oak Ridge National Laboratory. Oak Ridge, TN.

Teaching and service

Teaching

Instructor

Mining and Learning with Graphs (Lawrence Livermore National Laboratory, short course for the 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

EECS 376, Foundations of Computer Science (UMich, Fall 2016 and 2017)
CSE/Pol Sci 245A, Fair Division in Theory and Practice (WUSTL, Spring 2015)
CSE 417A, Introduction to Machine Learning (WUSTL, Fall 2014)

Selected program committees

WebConf 2021–2025
SDM 2021–2025
AAAI 2022–2025
IEEE BigData 2024
WSDM 2023
KDD 2021–2023
CIKM 2021–2023

Selected journal reviewing

Signal and Information Processing over Networks (IEEE)
Knowledge-based Systems (Elsevier)
Data Mining and Knowledge Discovery (Springer)
Transactions on Cybernetics (IEEE)
Knowledge and Information Systems (Springer)
Neural Computation (MIT Press)
Transactions on Computers (IEEE)
Transactions on Knowledge Discovery and Engineering (IEEE)