Tom Hartvigsen is an Assistant Professor of Data Science at the University of Virginia. He works to make machine learning trustworthy, robust, and socially responsible enough for deployment in high-stakes, dynamic settings. Tom's research has been published at many major peer-reviewed venues in Machine Learning, Natural Language Processing, and Data Mining. He is active in the machine learning community, serving as the General Chair for the Machine Learning for Health Symposium in 2023, helping organize the 2023 Conference on Health, Informatics, and Learning, and co-chairing workshops on time series and generative AI at NeurIPS'22 and ICML'23.
Prior to joining UVA, Tom was a Postdoctoral Associate at MIT's Computer Science and Artificial Intelligence Laboratory. He holds a Ph.D. and M.S. in Data Science from Worcester Polytechnic Institute and a B.A. in Applied Math from SUNY Geneseo.
Ph.D., Data Science, Worcester Polytechnic Institute
M.S., Data Science, Worcester Polytechnic Institute
B.A., Applied Mathematics, SUNY Geneseo
T. Hartvigsen, S. Gabriel, H. Palangi, M. Sap, D. Ray, E. Kamar. (2022). ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection. Annual Meeting of the Association for Computational Linguistics (ACL).
T. Hartvigsen, W. Gerych, J. Thadajarassiri, X. Kong, E. Rundensteiner. (2022). Stop&Hop: Early Classification of Irregular Time Series. ACM Internatonal Conference on Informaton and Knowledge Management (CIKM).
A. Balagopalan, H. Zhang, K. Hamidieh, T. Hartvigsen, F. Rudzicz, M. Ghassemi. (2022). The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations. ACM Conference on Fairness, Accountability, and Transparency (FAccT).
R. Doddaiah, P. Parvatharaju, E. Rundensteiner, T. Hartvigsen. (2022). Class-Specific Explainability for Deep Time Series Classifiers. International Conference on Data Mining (ICDM).
W. Gerych, T. Hartvigsen, L. Buquicchio, E. Agu, E. Rundensteiner. (2021) Recurrent Bayesian Classifier Chains for Exact Multi-label Classification. Advances in Neural Information
Processing Systems (NeurIPS)
T. Hartvigsen, C. Sen, X. Kong, E. Rundensteiner. (2020). Recurrent Halting Chain for Early Multi-label Classification. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).
C. Sen, T. Hartvigsen, B. Yin, X. Kong, E. Rundensteiner. (2020). Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? Annual Meeting of the Association for Computational Linguistics (ACL).
T. Hartvigsen, C. Sen, X. Kong, E. Rundensteiner. (2019). Adaptive-Halting Policy Network for Early Classification. ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Get the latest news
Subscribe to receive updates from the School of Data Science.