Overivew
Ajitesh Srivastava builds AI that helps public health see what’s coming. His work sits at the intersection of network processes, graph neural networks, Ajitesh Srivastava is an Associate Professor in AI and Health in the Bouvé College of Health Sciences, Khoury College of Computer Sciences, and Network Science Institute at Northeastern University. His research centers on graph machine learning, network science, dynamic systems, and combinatorial optimization, with a focus on addressing complex challenges in public health and social good. His work advances core artificial intelligence methodologies, including graph neural networks and optimization, and translates them into scalable computational tools for population health. Through these foundational techniques, he develops data-driven frameworks to understand epidemics and behavior and to optimize interventions.
His work has earned Best Paper Runner up Awards at KDD 2026 and AAAI 2024, a Google Faculty Research Award, and a win in DARPA’s Chikungunya Challenge, a global competition to forecast the virus’s spread across the Western Hemisphere.
He earned his PhD in computer science and later served as a Research Faculty at the University of Southern California. He holds a bachelor’s in computer science from the Birla Institute of Technology & Science, Pilani.
Selected Papers
Zeng, H., Zhou, H., Srivastava, A., Kannan, R., & Prasanna, V. (2020). GraphSAINT: Graph sampling based inductive learning method. In International Conference on Learning Representations (ICLR).
Borchering, R. K., … Srivastava, A., et al. (2021). Modeling of future COVID-19 cases, hospitalizations, and deaths, by vaccination rates and nonpharmaceutical intervention scenarios — United States, April–September 2021. Morbidity and Mortality Weekly Report, 70.
Srivastava, A. (2023). The variations of SIkJalpha model for COVID-19 forecasting and scenario projections. Epidemics, 45, 100729.
Al Aawar, M., Mutnuri, S., Montazerin, M., & Srivastava, A. (2025, April). Dynamics-based feature augmentation of graph neural networks for variant emergence prediction. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 27, pp. 27793-27801).
Srivastava, A., & Teng, S. (2026, August). Submodular Maximization under Supermodular Constraint: Greedy Guarantees. In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2 (pp. 4393-4404).
