Contact Information

Firstname = sunil

Lastname = gupta

Firstname.Lastname@deakin.edu.au

Current Position

I hold a senior Lecturer position in School of Information Technology at Deakin University, Australia. I am a founding member of the Strategic Research Centre for Pattern Recognition and Data Analytics (PRaDA). 

Research Interests

Machine Learning | Data Mining | Healthcare Analytics | Pervasive Computing | Social Media Analytics

  • Reinforcement Learning (Bayesian Optimization, Multi-arm Bandits)
  • Transfer learning, Multi-task learning.
  • Building predictive models for healthcare data.
  • Dimensionality reduction, Clustering,
  • Shared subspace learning: Modeling multiple data sources jointly.
  • Bayesian hierarchical modeling, Bayesian nonparametrics using Dirichlet and Beta processes.
  • Pervasive/Ubiquitous computing, Social media retrieval.

Education

PhD (Computing) at IMPCA, Curtin University, Australia  (2012) (PhD Thesis)

ME (Signal Processing) at Indian Institute Of Science, Bangalore, India  (2008)

B. Tech. (Electronics and Communication Engg.) at Harcourt Butler Technological Institute, Kanpur, India  (2001)

Work Experience

  • From Jan 2017, I am a senior lecturer at Deakin university, Geelong (Australia).
  • From Feb 2012 to Dec 2016, I was a lecturer at Deakin university, Geelong (Australia).
  • From Sep 2011 to Jan 2012, I worked at Curtin university, Perth (Australia) as a research fellow.
  • From Apr 2002 to May 2009, I worked at LRDE, Bangalore (India) as a research scientist.
Achievements
  • Our Stable Bayesian Optimization work won "Best Student Paper Awardat the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Springer 2017.
  • Our paper won "Finalists INTEL Track 5 Student Paper Award" at International Conference of Pattern Recognition, 2016.
  • Recipient of "Best Poster Award" at Asian Conference on Machine Learning, 2016.
  • Recipient of "Best Paper (Runner up) Award" at Asian Conference on Machine Learning, 2016.
  • Recipient of "Best Paper Awardat the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Springer 2015 for Multi- relational MTL paper.
  • Recipient of Best Papers of SDM, at SIAM Data Mining Conference 2014.
  • Recipient of Chancellor’s Commendation for excellence for my PhD thesis at Curtin University, 2012.

  • Recipient of KDD Travel Awards, ACM SIGKDD Data Mining Conference 2010.

  • Recipient of CIPRS Scholarship, Curtin University, Australia, 2009.

Courses Taught

2017: Machine Learning
2016: Machine Learning

Recent Publications

My external research profiles:  Google Scholar and ResearchGate.

The following material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyrigt holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Book Chapters

[2]S. Gupta, D. Phung, B. Adams, and S. Venkatesh. A matrix factorization framework for jointly analyzing multiple nonnegative data sources. In Katsutoshi Yada, editor, Data Mining for Service, pages 151--170. Springer, 2014. [ bib ]
[1]D. Phung, T. Nguyen, S. Gupta, and S. Venkatesh. Learning latent activities from social signals with hierarchical dirichlet process. In Gita Sukthankar, Christopher Geib, David V. Pynadath, Hung Bui, and Robert P. Goldman, editors, Handbook on Plan, Activity, and Intent Recognition, pages 149--174. Elsevier, 2013. [ bib ]

Journal

[18]Wei Luo, Dinh Phung, Truyen Tran, Sunil Gupta, Santu Rana, Chandan Karmakar, Alistair Shilton, John Yearwood, Nevenka Dimitrova, Bao Tu Ho, Svetha Venkatesh, and Michael Berk. Guidelines for developing and reporting machine learning predictive models in biomedical research: A multidisciplinary view. J Med Internet Res, 18(12):e323, Dec 2016. [ bib | DOI | http ]
[17]B Saha, S Gupta, D Phung, and S Venkatesh. Effective sparse imputation of patient conditions in electronic medical records for emergency risk predictions. Knowledge and Information Systems, page (to appear), 2016. [ bib ]
[16]B Saha, S Gupta, D Phung, and S Venkatesh. A framework for mixed-type multi-outcome prediction with applications in healthcare. The Journal of Biomedical and Health Informatics, page (to appear), 2016. [ bib ]
[15]P. Vellanki, T. Duong, S Gupta, D Phung, and S Venkatesh. Nonparametric discovery and analysis of learning patterns and autism subgroups from therapeutic data. Knowledge and Information Systems, page (to appear), 2016. [ bib ]
[14]S. Gupta, S. Rana, B. Saha, D. Phung, and S. Venkatesh. A new transfer learning framework with application to model-agnostic multi-task learning. Knowledge and Information Systems, pages (accepted on 28th Dec, 2015), 2015. [ bib ]
[13]I. Kamkar, S. Gupta, D. Phung, and S. Venkatesh. Stable feature selection for clinical prediction: Exploiting ICD tree structure using tree-lasso. Journal of Biomedical Informatics, 53:277--290, 2015. [ bib ]
[12]I. Kamkar, S. Gupta, D. Phung, and S. Venkatesh. Stabilizing l1-norm prediction models by supervised feature grouping. Journal of Biomedical Informatics, pages (accepted on 18th November, 2015), 2015. [ bib ]
[11]W Luo, T Nguyen, M Nichols, T Tran, S Rana, S Gupta, D Phung, S Venkatesh, and S Allender. Is demography destiny? application of machine learning techniques to accurately predict population health outcomes from a minimal demographic dataset. PLoS ONE, 2015. [ bib | DOI ]
[10]T.C. Nguyen, S. Gupta, D. Phung, and S. Venkatesh. Nonparametric discovery of movement patterns from accelerometer signals. Pattern Recognition Letters, pages (accepted on 20th Nov, 2015), 2015. [ bib ]
[9]T Nguyen, T Truyen, W Luo, S Gupta, S Rana, D Phung, M Nichols, L Millar, S Venkatesh, and S Allender. Web search activity data accurately predicts population chronic disease risk in the United States. Journal of Epidemiology & Community Health, page (accepted on 26 Jan 2015), 2015. [ bib | DOI ]
[8]T. C. Nguyen, S. Gupta, S. Venkatesh, and D. Phung. Continuous discovery of co-location contexts from bluetooth data. Pervasive and Mobile Computing, 16:286--304, 2015. [ bib ]
[7]S Rana, S Gupta, D Phung, and S Venkatesh. A predictive framework for modeling healthcare data with evolving clinical interventions. Statistical Analysis and Data Mining: The ASA Data Science Journal, 8(3):162--182, 2015. [ bib ]
[6]S Gupta, D Phung, and S Venkatesh. Modelling multilevel data in multimedia: A hierarchical factor analysis approach. Multimedia Tools and Applications, pages 1--23, 2014. [ bib | DOI ]
[5]S. Gupta, T. Tran, W. Luo, D. Phung, R. Kennedy, A. Broad, D. Campbell, D. Kipp, M. Singh, M. Khasraw, L. Matheson, D. Ashley, and S. Venkatesh. Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry. BMJ Open (DOI:10.1136/bmjopen-2013-004007), 2014. [ bib ]
[4]B Saha, S Gupta, D Phung, and S Venkatesh. Multiple task transfer learning with small sample sizes. Knowledge and Information Systems, pages 1--28, 2014. [ bib | DOI ]
[3]T Tran, W Luo, D Phung, S Gupta, S Rana, L Kennedy, A Larkins, and S Venkatesh. A framework for feature extraction from hospital medical data with applications in risk prediction. BMC bioinformatics, 15(1):6596, 2014. [ bib ]
[2]D. Phung, S. Gupta, T. Nguyen, and S. Venkatesh. Connectivity, online social capital and mood: A bayesian nonparametric analysis. IEEE Transactions on Multimedia, 15:1316--1325, May 2013. [ bib ]
[1]S Gupta, D Phung, B Adams, and S Venkatesh. Regularized nonnegative shared subspace learning. Data mining and knowledge discovery, 26(1):57--97, 2013. [ bib ]

Conference Papers

[46]Cheng Li, Sunil Gupta, Santu Rana, Alistair Shilton, and Svetha Venkatesh. High dimensional bayesian optimization using dropout. In The 26th International Joint Conference on Artificial Intelligence (IJCAI 2017), page (to appear), 2017. [ bib ]
[45]T. D. Nguyen, S. Gupta, S. Rana, and S. Venkatesh. Stable bayesian optimization. In Advances in Knowledge Discovery and Data Mining, page (accepted), Jeju, South Korea, 2017. Springer-Verlag Berlin Heidelberg. [ bib ]
[44]S Rana, C Li, V Nguyen, S Gupta, and S. Venkatesh. High dimensional bayesian optimization with elastic gaussian process. In International Conference on Machine Learning, page (to appear), Sydney, Australia, 2017. [ bib ]
[43]A. Shilton, S. Gupta, S. Rana, and S. Venkatesh. Regret bounds for transfer learning in bayesian optimisation. In The 20th International Conference on Artificial Intelligence and Statistics, page (accepted), Florida, USA, 2017. [ bib ]
[42]S Gupta, S Rana, and S Venkatesh. Differentially private multi-task learning. In Proceedings of Pacific Asia Workshop on Intelligence and Security Informatics, 2016. [ bib ]
[41]Haripriya Harikumar, Thin Nguyen, sunil Gupta, Santu Rana, Ramachandra Kaimal, and Svetha Venkatesh. Understanding behavioral differences between short and long-term drinking abstainers from social media. In Proceedings of the 12th International Conference on Advanced Data Mining and Applications (ADMA), Lecture Notes in Artificial Intelligence. Springer, 2016. [ bib ]
[40]Haripriya Harikumar, Thin Nguyen, Santu Rana, sunil Gupta, Ramachandra Kaimal, and Svetha Venkatesh. Extracting key challenges in achieving sobriety through shared subspace learning. In Proceedings of the 12th International Conference on Advanced Data Mining and Applications (ADMA), Lecture Notes in Artificial Intelligence. Springer, 2016. [ bib ]
[39]T. Joy, S. Rana, S. Gupta, and S. Venkatesh. Flexible transfer learning framework for bayesian optimisation. In Advances in Knowledge Discovery and Data Mining, page (accepted), Auckland, New Zealand, 2016. Springer-Verlag Berlin Heidelberg. [ bib ]
[38]T. Joy, S. Rana, S. Gupta, and S. Venkatesh. Hyperparameter tuning for big data using bayesian optimisation. In Proceedings of the 23rd International Conference on Pattern Recognition, page (to appear), Cancun, Mexico, 2016. [ bib ]
[37]I. Kamkar, S. Gupta, C. Li, D. Phung, and S. Venkatesh. Stable clinical prediction using graph support vector machines. In Proceedings of the 23rd International Conference on Pattern Recognition, page (to appear), Cancun, Mexico, 2016. [ bib ]
[36]C. Li, S. Gupta, S. Rana, V. Nguyen, and S. Venkatesh. Multiple adverse effects prediction in longitudinal cancer treatment. In Proceedings of the 23rd International Conference on Pattern Recognition, page (to appear), Cancun, Mexico, 2016. [ bib ]
[35]C. Li, S. Gupta, S. Rana, and S. Venkatesh. Toxicity prediction in cancer using multiple instance learning in a multi-task framework. In Advances in Knowledge Discovery and Data Mining, page (accepted), Auckland, New Zealand, 2016. Springer-Verlag Berlin Heidelberg. [ bib ]
[34]T Nguyen, S Gupta, S Rana, V Nguyen, and S Venkatesh. Cascade bayesian optimization. In 29th Australasian Joint Conference on Artificial Intelligence, Lecture Notes in Artificial Intelligence, pages (accepted on 12th September, 2016), Hobart, Australia, 2016. Springer. [ bib ]
[33]T. Nguyen, S. Gupta, S. Rana, and S. Venkatesh. Privacy aware k-means clustering with high utility. In Advances in Knowledge Discovery and Data Mining, page (accepted), Auckland, New Zealand, 2016. Springer-Verlag Berlin Heidelberg. [ bib ]
[32]V. Nguyen, S. Gupta, S. Rana, and S. Venkatesh. A bayesian nonparametric approach for multi-label classification. In Asian Conference on Machine Learning, page (accepted), 2016. [ bib ]
[31]V. Nguyen, S. Rana, S. Gupta, C. Li, and S. Venkatesh. Budgeted batch bayesian optimization. In IEEE International Conference on Data Mining, page (accepted), Barcelona, Spain, 2016. IEEE. [ bib ]
[30]B. Saha, S.K. Gupta, D. Phung, and S. Venkatesh. Transfer learning for rare cancer problems via discriminative sparse gaussian graphical model. In Proceedings of the 23rd International Conference on Pattern Recognition, page (to appear), Cancun, Mexico, 2016. [ bib ]
[29]S. Subramanian, S. Rana, S. Gupta, P. B. Sivakumar, S. Velayutham, and S. Venkatesh. Bayesian nonparametric multiple instance regression. In Proceedings of the 23rd International Conference on Pattern Recognition, page (to appear), Cancun, Mexico, 2016. [ bib ]
[28]S. Gupta, S. Rana, D. Phung, and S. Venkatesh. Collaborating differently on different topics: A multi-relational approach to multi-task learning. In Advances in Knowledge Discovery and Data Mining, pages 303--316, Ho Chi Minh City, Vietnam, 2015. Springer-Verlag Berlin Heidelberg. [ bib ]
[27]S. Gupta, S. Rana, D. Phung, and S. Venkatesh. What shall I share and with whom? - a multi-task learning formulation using multi-faceted task relationships. In Proceedings of the SIAM International Conference on Data Mining, pages 703--711, Vancouver, Canada, 2015. [ bib ]
[26]I Kamkar, S Gupta, D Phung, and S Venkatesh. Stable feature selection with support vector machines. In 28th Australasian Joint Conference on Artificial Intelligence, Lecture Notes in Artificial Intelligence, pages (accepted on 1st September, 2015), Canberra, Australia, 2015. Springer. [ bib ]
[25]I Kamkar, S Gupta, D Phung, and S Venkatesh. Exploiting feature relationships towards stable feature selection. In IEEE International Conference on Data Science and Advanced Analytics, pages (accepted on 23rd July, 2015), Paris, France, 2015. IEEE. [ bib ]
[24]S. Rana, S. Gupta, and S. Venkatesh. Differentially-private random forest with high utility. In IEEE International Conference on Data Mining, pages 955--960, NJ, USA, 2015. IEEE. [ bib ]
[23]B. Saha, S.K. Gupta, and S. Venkatesh. Prediction of emergency events: A multi-task multi-label learning approach. In Advances in Knowledge Discovery and Data Mining, pages 226--238, Ho Chi Minh City, Vietnam, 2015. Springer-Verlag Berlin Heidelberg. [ bib ]
[22]B Saha, S Gupta, and S Venkatesh. Improved risk predictions via sparse imputation of patient conditions in electronic medical records. In IEEE International Conference on Data Science and Advanced Analytics, pages (accepted on 23rd July, 2015), Paris, France, 2015. IEEE. [ bib ]
[21]T. C. Nguyen, S. Gupta, S. Venkatesh, and D. Phung. Fixed-lag particle filter for continuous context discovery using Indian buffet process. In 2014 IEEE International Conference on Pervasive Computing and Communications (PerCom), pages 20--28, Budapest, Hungary, March 2014. [ bib ]
[20]S. Gupta, S. Rana, D. Phung, and S. Venkatesh. Keeping up with innovation: A predictive framework for modeling healthcare data with evolving clinical interventions. In Proceedings of the SIAM International Conference on Data Mining, pages 235--243, Philadelphia, USA, 2014. [ bib ]
[19]T.C. Nguyen, S. Gupta, S. Venkatesh, and D. Phung. A Bayesian nonparametric framework for activity recognition using accelerometer data. In Proceedings of 22nd International Conference on Pattern Recognition (ICPR), pages 2017--2022, 2014. [ bib ]
[18]S. Rana, S.K. Gupta, D. Phung, and S. Venkatesh. Intervention-driven predictive framework for modeling healthcare data. In Advances in Knowledge Discovery and Data Mining, pages 497--508, Tainan, Taiwan, 2014. Springer-Verlag Berlin Heidelberg. [ bib ]
[17]S Gupta, D. Phung, and S. Venkatesh. Factorial multi-task learning: A Bayesian nonparametric approach. In International Conference on Machine Learning, pages 657--665, Atlanta, USA, 2013. [ bib ]
[16]T.V. Nguyen, D. Phung, S. Gupta, and S. Venkatesh. Interactive browsing system for anomaly video surveillance. In 2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), pages 384--389, Melbourne, Australia, 2013. [ bib ]
[15]T.C. Nguyen, D. Phung, S. Gupta, and S. Venkatesh. Extraction of latent patterns and contexts from social honest signals using hierarchical Dirichlet processes. In 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom 2013), pages 47--55, San Diego, USA, 2013. [ bib ]
[14]S. Venkatesh, D. Phung, T. Tran, and S. Gupta. Capitalising on the data deluge: Data analytics for healthcare. In Big Data. Health Informatics Society of Australia (HISA), 2013. [ bib ]
[13]S. Gupta, D. Phung, and S. Venkatesh. A slice sampler for restricted hierarchical beta process with applications to shared subspace learning. In Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, pages 316--325, Catalina Island, CA, USA, 2012. [ bib ]
[12]S Gupta, D Phung, and S Venkatesh. A Bayesian nonparametric joint factor model for learning shared and individual subspaces from multiple data sources. In Proceedings of the SIAM International Conference on Data Mining, pages 200--211, 2012. [ bib ]
[11]S. Gupta, S. Phung, and S. Venkatesh. A nonparametric bayesian poisson gamma model for count data. In Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, pages 1815--1818, Tsukuba, Japan, 2012. [ bib ]
[10]S. Gupta, D. Phung, B. Adams, and S. Venkatesh. A Bayesian framework for learning shared and individual subspaces from multiple data sources. In Advances in Knowledge Discovery and Data Mining, pages 136--147, Shenzhen, China, 2011. [ bib ]
[9]S. Gupta, D. Phung, B. Adams, and S. Venkatesh. A matrix factorization framework for jointly analyzing multiple nonnegative data sources. In Procs. of Text Mining Workshop, in conjuction with SIAM Int. Conf. on Data Mining, Arizona, USA, 2011. [ bib ]
[8]Y. Kumar, S. Gupta, B. Kiran, K. Ramakrishnan, and C. Bhattacharyya. Automatic summarization of broadcast cricket videos. In Consumer Electronics (ISCE), 2011 IEEE 15th International Symposium on, pages 222--225. IEEE, 2011. [ bib ]
[7]S. Gupta, D. Phung, B. Adams, T. Tran, and S. Venkatesh. Nonnegative shared subspace learning and its application to social media retrieval. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1169--1178. ACM, 2010. [ bib ]
[6]S. Gupta, S. Ghose, and D. Seshagiri. Modelling of sea clutter and detection of low observable sea surface targets. In International Radar Symposium India, pages 423--427, 2009. [ bib ]
[5]V. Kulkarni, S. Gupta, R. Badrinath, and D. Seshagiri. A maximum likelihood estimator for elevation angle in presence of multipath using two beams. In International Radar Symposium India, pages 67--69, 2009. [ bib ]
[4]S. Gupta, Y. Kumar, and K. Ramakrishnan. Learning feature trajectories using gabor filter bank for human activity segmentation and recognition. In Proceedings of the 6th IEEE Indian Conference on Computer Vision, Graphics & Image Processing (ICVGIP) 2008, pages 111--118, Bhubaneswar, India, 2008. [ bib ]
[3]S. Gupta, D. Seshagiri, and S. Ravid. On the effects of atmospheric refractions on multipath phenomenon for low angle tracking. In International Radar Symposium India, 2005. [ bib ]
[2]S. Gupta, D. Seshagiri, and S. Ravid. A generic centroiding algorithm. In International Radar Symposium India, 2005. [ bib ]
[1]S. Gupta, K. Venkatesha, and S. Ravid. Radar signal processor simulator. In International Radar Symposium India, 2003. [ bib ]

Last Modified:Wednesday, May 24, 2017 09:30

.

Student Supervision
Thuong Nguyen (completed), Iman Kamkar (completed), Thanh Dai Nguyen (ongoing), Anil Ramachandran (ongoing)