I am a researcher 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 have worked on new graph neural network methods and applications to molecular modeling, scientific image segmentation, and software analysis. More recently, I have also begun working on research in foundation models and their applications to problems in biomedicine and materials science.
Publications
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. Generating Protein Structures for Pathway Discovery Using Deep Learning. Journal of Chemical Theory and Computation 2024.
- Mark Heimann, Christine Klymko, Jayaraman J. Thiagarajan. Adapting Large Language Models to Predict Gene Interactions. BioKDD @ KDD 2024.
- Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra, and Jayaraman Thiagarajan. Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks. ICLR 2024. Also presented at DMLR @ ICML 2023, GLFrontiers @ NeurIPS 2023.
- Donald Loveland, Jiong Zhu, Mark Heimann, Benjamin Fish, Michael T Schaub, and Danai Koutra. On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks. LOG 2023.
- Jiong Zhu, Yujun Yan, Mark Heimann, Lingxiao Zhao, Leman Akoglu, and Danai Koutra. Heterophily and Graph Neural Networks: Past, Present, and Future." IEEE Data Engineering Bulletin, 2023.
- Samuel Leventhal, Attila Gyulassy, Valerio Pascucci, and Mark Heimann. Modeling Hierarchical Topological Structure in Scientific Images with Graph Neural Networks. ICIP 2023. Also accepted at GLFrontiers at NeurIPS 2022.
- Samuel Leventhal, Attila Gyulassy, Mark Heimann, and Valerio Pascucci. Exploring Classification of Topological Priors with Machine Learning for Feature Extraction.” TVCG 2023.
- Rakshith Subramanyam, Mark Heimann, Jayram Thathachar, Rushil Anirudh, and Jayaraman J. Thiagarajan. Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification. WACV 2023.
- Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann, Danai Koutra, and Jayaraman Thiagarajan. Understanding Self-Supervised Graph Representation Learning from a Data-Centric Perspective. NeurIPS 2022. Also accepted at GLB @ WebConf 2022, MLG @ KDD 2022.
- Jing Zhu, Danai Koutra, and Mark Heimann. CAPER: Coarsen, Align, Project, Refine – A General Multilevel Framework for Network Alignment. CIKM 2022.
- Donald Loveland, Jiong Zhu, Mark Heimann, Ben Fish, Michael Schaub, and Danai Koutra. On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods. DLG @ KDD, 2022.
- Konstantia Georgouli, Helgi I. Ingólfsson, Fikret Aydin, Mark Heimann, Felice Lightstone, Peer-Timo Bremer, Harsh Bhatia. Emerging Patterns in the Continuum Representation of Protein-Lipid Fingerprints. CompBio @ ICML 2022.
- Mark Heimann, Xiyuan Chen, Fatemeh Vahedian, and Danai Koutra. Refining Network Alignment to Improve Matched Neighborhood Consistency. SIAM International Conference on Data Mining (SDM), 2021. [code]
- Jing Zhu*, Xingyu Lu*, Mark Heimann, and Danai Koutra. Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding. SIAM International Conference on Data Mining (SDM), 2021. [code]
- Junchen Jin, Mark Heimann, Di Jin, and Danai Koutra. Towards Understanding and Evaluating Structural Node Embedding. TKDD 2021. [code] Also invited for contributed talk at KDD MLG 2020 [code] [video]
- Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs. Conference on Neural Information Processing Systems (NeurIPS), 2020. [code]
- Mark Heimann, Goran Murić, and Emilio Ferrara. Structural Node Embedding in Signed Social Networks: Finding Online Misbehavior at Multiple Scales. International Conference on Complex Networks and their Applications (Complex Networks), 2020. [code]
- Xiyuan Chen, Mark Heimann, Fatemeh Vahedian, and Danai Koutra. CONE-Align: Consistent Network Alignment with Proximity-Preserving Node Embedding. International Conference on Information and Knowledge Management (CIKM), 2020. Also accepted at KDD MLG Workshop 2020 [code] [video]
- Kai Qin, Flora D. Salim, Yongli Ren, Wei Shao, Mark Heimann and Danai Koutra. G-CREWE: Graph CompREssion With Embedding for Network Alignment. International Conference on Information and Knowledge Management (CIKM), 2020. [code]
- Mark Heimann, Tara Safavi, and Danai Koutra. Distribution of Node Embeddings as Multiresolution Features for Graphs. IEEE International Conference on Data Mining (ICDM), 2019. Best Student Paper [code]
- Di Jin, Mark Heimann, Ryan Rossi, and Danai Koutra. node2bits: Compact Time- and Attribute-aware
Node Representations for User Stitching. European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), 2019. [code]
- Di Jin*, Mark Heimann*, Tara Safavi, Mengdi Wang, Wei Lee, Lindsay Snider, and Danai Koutra. Smart Roles: Inferring Professional Roles in Email Networks. Conference on Knowledge Discovery and Data Mining (KDD), 2019. [code]
- Mark Heimann, Haoming Shen, Tara Safavi, and Danai Koutra. REGAL: Representation Learning-based Graph Alignment. International Conference on Information and Knowledge Management (CIKM), 2018. [code]
- Mark Heimann*, Wei Lee*, Shengjie Pan, Kuan-Yu Chen, and Danai Koutra. HashAlign: Hash-Based Alignment of Multiple Graphs. Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2018. [code]
- Yujun Yan, Mark Heimann, Di Jin, and Danai Koutra. Fast Flow-based Random Walk with Restart in a Multi-query Setting. SIAM International Conference on Data Mining (SDM), 2018. [code]
*Equal contribution