Srinivasan Parthasarathy

Professor

Dept. of Computer Science and Engineering and Department of Biomedical Informatics 
The Ohio State University 
395 Dreese Lab
2015 Neil Ave 
Columbus, OH-43210, USA

Office: 693 Dreese Lab 
Phone: (614) 292-2568
Fax: (614) 292-2911
Email: s r i n i [AT] cse.ohio-state.edu (remove spaces in name and replace [AT] with appropriate symbol)
WWW: http://www.cse.ohio-state.edu/~ (my-last-name.2)


Teaching

I primarily teach courses in the Data and Network Science areas. In the past I have taught courses in Computer Architecture. Recent courses I have taught include:

CSE 5243 (Introduction to Data Mining)

CSE 5249 (Special Topics Seminar in Databases and Data Mining)

CSE 5245 (Introduction to Network Science)


Research

I direct the Data Mining Research Laboratory which is a part of the High End Systems Group and affiliated with the Laboratory for Artificial Intelligence Research. I am broadly interested in the following areas

  1. High Performance Data Analytics
  2. Graph Analytics and Network Science
  3. Machine Learning and Database Systems

I enjoy applied, systems and theoretical problems in these areas. The National Science Foundation, the Department of Energy and the National Institutes of Health have been the primary supporters of my group's research together with grants and gifts from several industrial sponsors. For a recent example, read more here.

PhD Advisees

I currently advise the following PhD students (research foci noted):


The following have graduated but continue to be remembered fondly:

o   Matthew Otey (PhD 2006, @Google Research)

o   Hui Yang (PhD 2006, Assoc. Prof @San Francisco State University)

o   Sameep Mehta (PhD 2006, Manager@IBM Research )

o   Michael Twa (PhD 2006, Assoc. Dean, @U. Alabama)

o   Keith Marsolo (PhD 2007, Assoc. Prof@Cincinnati Childrens and Univ. of Cincinnati)

o   Amol Ghoting (PhD 2007,  @LinkedIn)

o   Chao Wang (PhD 2008,Senior Applied Researcher @Microsoft )

o   Gregory Buehrer (PhD 2008,  Partner Architect@Microsoft)

o   Sitaram Asur, (PhD 2009,   now @Doximity)

o   Duygu Ucar, (PhD 2009, Asst. Professor @Jackson Laboratories)

o   Shirish Tatikonda (PhD 2010,  @Target Labs)

o   V. Satuluri (PhD 2011,   @Twitter)

o   X. Yang (PhD 2012,   @Google)

o   Y. Wang (PhD 2013,  @Airbnb)

o   Y-K Shih (PhD 2013,   @Facebook)

o   T. Clemons, (ABD 2014, @Manta)

o   S.M. Faisal (PhD 2015, @Google)

o   Y. Ruan (PhD 2015, @Google)

o   D. Fuhry (PhD 2015, Senior Lecturer @OSU)

o   Y. Zhang (PhD 2015,  @Google)

o    

I also advise undergraduate students and masters students (at some point I will update this list to include them as well).

Selected Awards and Honors

Selected Recent Publications

High Performance Analytics: My earlier efforts in this space include the development of the ECLAT family of algorithms (a precursor by at least a decade or two to the current emphasis on column oriented systems designs) for association analysis in the late nineties, the development of novel architecture conscious designs for various analytic algorithms on both shared memory and distributed memory systems (through careful data placement and the judicious leveraging of architecture and network capabilities such as RDMA). My current efforts in this space largely target graph algorithms on GPUs and systems that support scalable energy-conscious analytics (via elastic fidelity or via green-energy harvesting). Selected recent papers in this vein include:

o    A. Chakrabarti, S. Parthasarathy and C. Stewart, A Pareto Framework for Data Analytics on Heterogeneous Systems: Implications for Green Energy Usage and Performance, to appear at the IEEE International Conference on Parallel Processing (ICPP), 2017.

o    G. Tziantzioulis, A. Gok, S. Faisal, N. Hardavellas, S. Memik and S. Parthasarathy, Lazy Pipelines: Enhancing quality in approximate computing. DATE 2016.

o    G. Tziantzioulis, A. Gok, S. Faisal, N. Hardevallas, S. Memik and S. Parthasarathy: b-HiVE: a bit-level history-based error model with value correlation for voltage-scaled integer and floating point units. IEEE DAC 2015: 105:1-105:6

o    S. M. Faisal, G. Tziantzioulis, A. M. Gok, N. Hardavellas, S. Memik, S. Parthasarathy: Edge Importance Identification for Energy Efficient Graph Processing, IEEE Big Data Conference, 2015.

o    Gregory Buehrer, Roberto L. de Oliveira Jr., David Fuhry, Srinivasan Parthasarathy: Towards a parameter-free and parallel itemset mining algorithm in linearithmic time. ICDE 2015: 1071-1082

o    Naser Sedaghati, Te Mu, Louis-Noel Pouchet, Srinivasan Parthasarathy, P. Sadayappan: Automatic Selection of Sparse Matrix Representation on GPUs. ACM International Conference on Supercomputing (ICS) 2015: 99-108

o    Arash Ashari, Naser Sedaghati, John Eisenlohr, Srinivasan Parthasarathy, P. Sadayappan: Fast Sparse Matrix-Vector Multiplication on GPUs for Graph Applications. SC 2014: 781-792

o    S. M. Faisal, Srinivasan Parthasarathy, P. Sadayappan: Global graphs: A middleware for large scale graph processing. IEEE Big Data Conference 2014: 33-40

o    Qingpeng Niu, Pai-Wei Lai, S. M. Faisal, Srinivasan Parthasarathy, P. Sadayappan: A fast implementation of MLR-MCL algorithm on multi-core processors. HiPC 2014: 1-10

Graph Analytics and Network Science: My work in this space was initiated roughly a decade ago. Our initial efforts in this space focused on event-based algorithms for dynamic network analysis, Markov clustering and ensemble clustering of networks with applications in bioinformatics and clinical informatics. Current foci are in the  space of computational social science (with applications to emergency response and behavioral health) and the theoretical understanding of various network sampling and localized sparsification algorithms. Selected recent papers in this vein include:

o    N.Vedula and S. Parthasarathy: Emotional and Linguistic Cues of Depression from Social Media, In ACM International Conference on Digital Health (ACM-DH17), 2017

o    P. Gupte, B. Ravindran and S. Parthasarathy, Role Discovery in Graphs using Global Features: Algorithms, Applications and a Novel Evaluation Strategy, IEEE International Conference on Data Engineering, ICDE 2017.

o    Sarvenaz Choobdar, Pedro Manuel Pinto Ribeiro, Srinivasan Parthasarathy, Fernando M. A. Silva: Dynamic inference of social roles in information cascades. Data Min. Knowl. Discov. 29(5): 1152-1177 (2015)

o    Yu-Keng Shih, Sungmin Kim, Yiye Ruan, Jinxing Cheng, Abhishek Gattani, Tao Shi, Srinivasan Parthasarathy: Component Detection in Directed Networks. CIKM 2014.

o    Yiye Ruan, Srinivasan Parthasarathy: Simultaneous detection of communities and roles from large networks. ACM COSN 2014: 203-214

o    Hemant Purohit, Yiye Ruan, David Fuhry, Srinivasan Parthasarathy, Amit P. Sheth: On Understanding the Divergence of Online Social Group Discussion. ICWSM 2014

Machine Learning and Database Systems: My past work in this space focused on scalable anomaly detection, similarity search (for non-metrics) and the application of machine learning algorithms arising in a clinical context. My current interests include usable database systems (e.g. query by output, visual query interfaces), algorithms for similarity search (with an emphasis on locality sensitive hashing), contextual anomaly detection, and optimization algorithms that arise in machine learning. Selected recent papers in this vein include:

o    J. Liang, S. Parthasarathy: Robust Contextual Outlier Detection: Where Context Meets Sparsity. ACM Conference on Information and Knowledge Management (CIKM 2016) (full version available on arXiv)

o    A. Chakrabarti, V. Satuluri, A. Srivathsan and S. Parthasarathy, A Bayesian Perspective on Locality Sensitive Hashing with Extensions for Kernel Methods, in ACM Transactions on KDD, 2016.

o    A. Roychowdhury, B. Kulis and S. Parthasarathy, Robust Monte Carlo Sampling using Riemannian Nose Poincare Hamiltonian Dynamics,ICML 2016.

o    R. Cai, Z. Zhang, S. Parthasarathy, A. Tung, Z. Hao and W. Zhang., Multi-Domain Manifold Learning for Drug Target Interaction Prediction, SIAM SDM 2016.

o    J. Liang, D. Fuhry, D. Maung, A. Borstad, R. Crawfis, L. Gauthier, A. Nandi and S. Parthasarathy, A Data Analytics Framework for A Game-based Rehabilitation System. ACM Conference on Digital Health, 2016.

o    Aniket Chakrabarti, Srinivasan Parthasarathy: Sequential Hypothesis Tests for Adaptive Locality Sensitive Hashing. WWW 2015: 162-172

o    Quoc Trung Tran, Chee Yong Chan, Srinivasan Parthasarathy: Query reverse engineering. VLDB J. 23(5): 721-746 (2014)

o    Roberto Lourenco de Oliveira Jr., Adriano Veloso, Adriano M. Pereira, Wagner Meira Jr., Renato Ferreira, Srinivasan Parthasarathy: Economically-efficient sentiment stream analysis. SIGIR 2014: 637-646

For a complete listing of publications please refer to one of the links below: Google Scholar, DBLP or PubMed. If you are at this page searching for a frequently requested code base please check here.

 


Service

I serve or have served on the program committees or organizing committees of leading conferences in the fields of Machine Learning, Data Mining, Parallel and Distributed Computing, and Database Systems. I serve or have served as action or associate editors of several leading journals in these fields. Since 2012 I am the Steering Committee Chair of the SIAM Data Mining Conference Series.

 

At OSU, I helped create, and am a founding co-director of its undergraduate major in data analytics. This major among the first of its kind nationwide spans the core areas of Computer Science, Statistics and Mathematics while offering specializations in a diverse range of domains ranging from business analytics to cybersecurity and from text analytics to health informatics. For more details on this effort please go to the DA major website.

 


Last Update: April 2017

analytics tool