Computer Scientist
Auto Learning & Reasoning Group
Computer Scientist
Auto Learning & Reasoning Group


Khushbu Agarwal is a senior computer scientist at Pacific Northwest National Laboratory (PNNL) with more than 12 years of experience in data analytics. Her primary interests are in deriving human actionable knowledge from large corpus of data, using a combination of symbolic and neural learning. She has extensive experience working on graph analytics, knowledge bases, representation learning, and building prediction and reasoning systems, to apply them for solving real-world application needs. Her recent work focuses on building intelligent medical systems that combine different modalities of healthcare data into a single unified deep learning framework for prediction and reasoning in the context of diseases.

Research Interest

  • Deep Learning
  • Graph Analytics
  • Knowledge Representation
  • Large-Scale Graph Analytics
  • Machine Learning
  • Knowledge Base
  • High-performance Computing (HPC).


  • MS in Computer Science and Engineering, The Ohio State University, USA
  • BE in Computer Science and Engineering, Birla Institute of Technology, India.

Affiliations and Professional Service

  • Institute of Electrical and Electronics Engineers (IEEE) Women in Engineering.

Awards and Recognitions

  • R&D 100 Award for Streamworks (2018)
  • Transition to Practice Award for Streamworks, Department of Homeland Security (2016-2017)
  • Outstanding Performance Award, PNNL (2015, 2016, and 2018)
  • University Fellow, The Ohio State University (2005-2006).


  • US Patent No. 10,810,210, October 20, 2020, “Performance and usability enhancements for continuous subgraph matching queries on graph-structured data”
  • U.S. Patent No. 10,855,706, April 12, 2018, “System and methods for automated detection, reasoning and recommendations for resilient cyber systems”.



  • Nandanoori S.P., S. Guan, S. Kundu, S. Pal, K. Agarwal, Y. Wu, S. Choudhury. 2022. “Graph Neural Network and Koopman Models for Learning Networked Dynamics: A Comparative Study on Power Grid Transients Prediction.” IEEE Access. arXiv preprint arXiv 2202.08065
  • Nandanoori S., S. Pal, S. Sinha, S. Kundu, K. Agarwal, and S. Choudhury. 2022. "Data-driven Distributed Learning of Multi-agent Systems: A Koopman Operator Approach." In IEEE Control and Decision Conference. PNNL-SA-160981. doi:10.1109/CDC45484.2021.9682872


  • Wang P., K. Agarwal, C. Ham, S. Choudhury, C.K. Reddy. 2021. “Self-supervised learning of contextual embeddings for link prediction in heterogeneous networks.” Proceedings of The Web Conference, 2946-2957. arXiv preprint arXiv.2007.11192


  • Nandanoori S., S. Kundu, S. Pal, K. Agarwal, and S. Choudhury. 2020. "Model-Agnostic Algorithm for Real-Time Attack Identification in Power Grid using Koopman Modes." In IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (IEEE SmartGridComm 2020), November 11-13, 2020, Tempe AZ, 1-6. Piscataway, New Jersey: IEEE. PNNL-SA-154191. doi:10.1109/SmartGridComm47815.2020.9303022



  • Choudhury S., S. Purohit, P. Lin, Y. Wu, L.B. Holder, and K. Agarwal. 2018. "Percolator: Scalable Pattern Discovery in Dynamic Graphs." In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM 2018), February 5-9, 2018, Los Angeles, California, 759-762. New York, New York: ACM. PNNL-SA-128916. doi:10.1145/3159652.3160589
  • Corley C.D., N.O. Hodas, E.H. Yeung, A.M. Tartakovsky, T.J. Hagge, S. Choudhury, and K. Agarwal, et al. 2018. "Deep Learning for Scientific Discovery." The Next Wave 22, no. 1:27-31. PNNL-SA-129480.


  • Castellana V.G., M. Minutoli, S. Bhatt, K. Agarwal, J.T. Feo, D.G. Chavarria Miranda, and D.J. Haglin. 2017. "High-Performance Data Analytics Beyond the Relational and Graph Data Models with GEMS." In IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW 2017), May 29-June 2, 2017, Orlando, Florida, 1029-1038. Piscataway, New Jersey: IEEE. PNNL-SA-124655. doi:10.1109/IPDPSW.2017.70
  • Choudhury S., K. Agarwal, S. Purohit, B. Zhang, M.A. Pirrung, W.P. Smith, and M. Thomas. 2017. "NOUS: Construction and Querying of Dynamic Knowledge Graphs." In IEEE 33rd International Conference on Data Engineering (ICDE 2017), April 19-22, 2017, San Diego, California, 1563-1565. Piscataway, New Jersey: IEEE. PNNL-SA-123812. doi:10.1109/ICDE.2017.228


  • Zhang B., S. Choudhury, M. Al-Hasan, X. Ning, K. Agarwal, S. Purohit, and P. Pesantez. 2016. "Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs." In Third Workshop on Mining Networks and Graphs: A Big Data Analytic Challenge (MNG 2016), May 7, 2016, Miami, Florida. Philadelphia, Pennsylvania: Society for Industrial and Applied Mathematics (SIAM). PNNL-SA-115550.


  • Choudhury S., L. Holder, G. Chin, K. Agarwal, and J.T. Feo. 2015. "A Selectivity based approach to Continuous Pattern Detection in Streaming Graphs." In Proceedings of the 18th International Conference on Extending Database Technology (EDBT), March 23-27, 2015, Brussels, Belgium, 157-168. Konstanz: PNNL-SA-107908. doi:10.5441/002/edbt.2015.15
  • Scheibe T.D., K.L. Schuchardt, K. Agarwal, J.M. Chase, X. Yang, B.J. Palmer, and A.M. Tartakovsky, et al. 2015. "Hybrid multiscale simulation of a mixing-controlled reaction." Advances in Water Resources 83. PNNL-SA-105960. doi:10.1016/j.advwatres.2015.06.006
  • Vishnu A., and K. Agarwal. 2015. "Large Scale Frequent Pattern Mining using MPI One-Sided Model." In IEEE International Conference on Cluster Computing (CLUSTER 2015), September 8-11, 2015, Chicago, Illinois, 138-147. Piscataway, New Jersey:IEEE. PNNL-SA-110836. doi:10.1109/CLUSTER.2015.30


  • Ciraci S., J.A. Daily, J.C. Fuller, A.R. Fisher, L.D. Marinovici, and K. Agarwal. 2014. "FNCS: A Framework for Power System and Communication Networks Co-Simulation." In DEVS 2014: Proceedings of the Symposium on Theory of Modeling & Simulation, April 13-16, 2014, Tampa, Florida, Article No. 36. San Diego, California: Society for Computer Simulation International. PNNL-SA-100344.
  • Ciraci S., J.A. Daily, K. Agarwal, J.C. Fuller, L.D. Marinovici, and A.R. Fisher. 2014. "Synchronization Algorithms for Co-Simulation of Power Grid and Communication Networks." In IEEE 22nd International Symposium on Modeling Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS 2014), September 9-11, 2014, Paris, France, 355-364. Piscataway, New Jersey: IEEE. PNNL-SA-101723. doi:10.1109/MASCOTS.2014.51
  • Scheibe T.D., X. Yang, K.L. Schuchardt, K. Agarwal, J.M. Chase, B.J. Palmer, and A.M. Tartakovsky. 2014. "A Many-Task Parallel Approach for Multiscale Simulations of Subsurface Flow and Reactive Transport." In 7th Workshop on Many-Task Computing on Clouds, Grids, and Supercomputers (MTAGS 2014), November 16, 2014, New Orleans, Louisiana. New York, New York: ACM. PNNL-SA-105263.


  • Agarwal K., P. Sharma, J. Ma, C. Lo, I. Gorton, and Y. Liu. 2013. "REVEAL: An Extensible Reduced Order Model Builder for Simulation and Modeling." Computing in Science & Engineering 16, no. 2:44-53. PNNL-SA-90857. doi:10.1109/MCSE.2013.46
  • Chavarría-Miranda D., K. Agarwal, and T. Straatsma. 2013. "Scalable PGAS Metadata Management on Extreme Scale Systems." In 13th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid'13), May 13-16, 2013, Delft, Netherlands, edited by P Balaji, D Epema and T Fahringer, 103-111. Los Alamitos, California: IEEE Computer Society. PNNL-SA-93214. doi:10.1109/CCGrid.2013.83
  • Pan W., J. Bao, C. Lo, C. Lai, K. Agarwal, B.J. Koeppel, and M.A. Khaleel. 2013. "A general approach to develop reduced order models for simulation of solid oxide fuel cell stacks." Journal of Power Sources 232. PNNL-SA-90310. doi:10.1016/j.jpowsour.2013.01.057


  • Agarwal K., J.M. Chase, K.L. Schuchardt, T.D. Scheibe, B.J. Palmer, and T.O. Elsethagen. 2011. "Design and Implementation of “Many Parallel Task” Hybrid Subsurface Model." In MTAGS '11: Proceedings of the 2011 ACM International Workshop on Many Task Computing on Grids and Supercomputers, November 12-18, 2011, Seattle, Washington, 25-32. New York, New York: Association for Computing Machinery. PNNL-SA-83048. doi:10.1145/2132876.2132884
  • Yin J., K. Agarwal, M. Krishnan, D. Chavarría-Miranda, I. Gorton, and T.G. Epperly. 2011. "Implementing High Performance Remote Method Invocation in CCA." In IEEE International Conference on Cluster Computing (CLUSTER 2011), September 26-30, 2011, Austin, Texas, 547-551. Los Alamitos, California: IEEE Computer Society. PNNL-SA-81450. doi:10.1109/CLUSTER.2011.78


  • Krishnamoorthy S., and K. Agarwal. 2010. "Scalable Communication Trace Compression." In The 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, 408-417. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers. PNNL-SA-70735. doi:10.1109/CCGRID.2010.111
  • Schuchardt K.L., K. Agarwal, J.M. Chase, M.L. Rockhold, V.L. Freedman, T.O. Elsethagen, and T.D. Scheibe, et al. 2010. "Task parallel sensitivity analysis and parameter estimation of groundwater simulations through the SALSSA framework." In Proceedings of the 2010 Scientific Discovery through Advanced Computing (SciDAC) Conference, July 11-15, 2010, Chattanooga, Tennessee, 233-237. Oak Ridge, Tennessee: Oak Ridge National Laboratory. PNNL-SA-73770.
  • Shah A.R., K. Agarwal, E.S. Baker, M. Singhal, A.M. Mayampurath, Y.M. Ibrahim, and L.J. Kangas, et al. 2010. "Machine learning based prediction for peptide drift times in ion mobility spectrometry." Bioinformatics 26, no. 13:1601-1607. PNWD-SA-8802. doi:10.1093/bioinformatics/btq245