sahely

Profile picture for user sahely
Dr. Sahely Bhadra
Asst. Professor
Department
Email Me
Biosketch
  • Assistant Professor (Jun, 2017 -Till date)
    • Computer Science and Engineering, IIT Palakkad, India
  • Postdoctoral researcher
    • Network Science Institute, Northeastern University, USA (Jan, 2017 - May 2017)
    • Helsinki Institute of Information Technology, Aalto University, Finland (Oct,2014 - Dec,2016)
    • Max-Planck-Institute for Informatik and Saarland University, Germany (Sep, 2012 - Aug, 2014)
  • Research Internship
  • PhD in Computer Science (Aug, 2006 - Sep, 2012)
  • Software Engineer (Jul, 2004 - Jul, 2006)
    • Wipro Technology, Bangalore
  • B.Tech in Information Technology (Apr, 2000-May, 2004)
    • RCC Institute of Information Technology, Kalyani University, Kolkata
Research

Research interest:

Machine Learning (learning from noisy, incomplete data and multi-view data), optimization (robust optimization and convex optimization for large data), Time series data (anomaly detection), bio-informatics (micro-array data analysis and molecular network analysis).

Summary:

I am currently working on detecting and predicting extreme events in time series data using machine learning models and deep learning models and on handling missing data for kernel method when data has multiple sources. Previously, I have worked on robust optimization to learn form noisy data. My recent work proposes a new pre-processing method to correct noisy labels via mutual consistency check using a Parzen window classifier. It has also used the Spannogram framework to solve the problem with approximation guarantees. During my graduation I have been working on building robust classifiers to deal with interval-valued uncertainty in data as well as kernel matrices. I have also dealt with scalability and robustness of these classifiers. A novel distribution free large deviation inequality has been proposed which handles uncertainty. A mirror descent algorithm (MDA) like procedures have been applied to make learning of proposed robust formulations scalable. In addition to working on the mathematical aspects, I focused on applying new formulations on various real life scenarios.

Awards:

                 Indo-Finish Mobility grand 2019-2020 from DST and Academy of Finland (June-July 2019).

                 IMPECS postdoc fellowship, 2012-2014.

                 IBM Ph.D. Fellowship Award 2010 - 2011.

                 Best Runner Up paper award in PAKDD, 2009.

Research Grant:

  1.  Core Research Grand (CRG) from SERB, DST of around INR 3.5m on Project titled "Robust Multi-view Learning for Extreme Events Detection and Prediction in Time Series Data “. 2021-2024.
  2. Automatic Pathogen Detection in plants (as Co-investigator ) a project in TIH of IITPalakkad

 

 

Teaching

February - May, 2021

    CS3700: Introduction to Database Systems (S6, Core, Theory)

December -February 2020

CS5512: Machine Learning (MTech Data Science S1 , Research Scholar, Elective)

CS5101: Machine Learning Lab(MTech Data Science S1, Research Scholar, Elective)

January -April 2020

CS5512: Machine Learning (S5 Research Scholar, Elective)

CS3145:  Introduction to Database Systems Lab (S6, Core, Laboratory)

August -December 2019

    CS2300: Data Structure and Algorithm (S3, Core, Theory)

CS2310: Data Structure and Algorithm Lab (S3, Core, Laboratory)

January - April 2019

    CS3700: Introduction to Database Systems (S6, Core, Theory)

CS3145:  Introduction to Database Systems Lab (S6, Core, Laboratory)

August -December 2018

CS4801: Principles of Machine Learning (S5, Elective)

CS5001: Topics in Machine Learning(S7, Research, Elective)

January - April, 2018

CS4804: Convex Optimization (S6, elective)

CS3700: Introduction to Database Systems (S6, Core, Theory)

CS3145:  Introduction to Database Systems Lab (S6, Core, Laboratory)

August -December, 2017

CS4801: Principles of Machine Learning (S5, Elective)

CS2110 Computer Programming Lab (S3, Core, Laboratory)

Research Group

PhD Students:

   Ms Abilasha (since August,2018 in IITPKD)

   Ms Jishy (since August 2019, External registration in IITPKD)  

MSc Students:   

   Shikha (since August 2019 in IITPKD)

Graduated PhD Students:

     Viivi Uurtio (co-supervising with Prof Juho Rousu of Aalto University, Finland)

BTech projects students:

     Ahmed Zaheer Dadarkar (2017-2021): Extreme Value prediction in Time series data

     Vipin Kumar Seth (2017-2021): Rainfall prediction in a small region around Palakkad 

     Ipsita Singh  (2016-2020): Learning Graph Embedding for Graph Classification

     Adrian McDonald Tariang (2015-2019):  Automated Newspaper Typesetting based on News Values and Prior Editorial Style

     Akshat Choube(2015-2019): Study of Multiview Face Synthesis Using Generative Adversarial Networks (GANs)

     Anish MM (2015-2019): Unsupervised Lower Dimensional Representation Learning for Time Series Data

     Prabal  Vashisht (2015-2019): Multi-view data interpretation and completion using Deep Networks

Intern:

      Kaveri Mukundan, BTech.

      Soumya Suvra Ghosal, 2nd year, NIT Durgapur

Research Area
Machine Learning
Optmization
Bioinformatics
Additional Information
Title
Other Professional Positions
Description

Organizing:

  • Workshop on Smart and Precise Agriculture in PAKDD 2021. 
  • One-day Symposium on Data Science in IIT Palakkad 2020.

  • Young Researchers’ Symposium Chairs in CODS COMAD 2019

Program committee member:

NIPS (2018,2019,2020), IJCAI (2018, 2019,2020), ICML (2019,2020,2021) DSAA 2018, KDD 2017

Reviewer:

IEEE PAMI, Bioinformatics, PlosOne

Participation:

Represent IITPKD in WOMEN SCIENTIST & ENTREPRENEUR’S CONCLAVE in Indian International Science Festival 2017

Title
Invited Talk
Description

'Principle Flux mode analysis', Indo-German Frontiers of Engineering Conference (INDOGFOE 2021) Symposium, by IIT KGP, 24 February - 26 February 2021

'Linear Models for Classification', The ACM India summer school on ML and Data Science, by IITM, 4th June - 13th June 2018.

'Machine Learning in Bioinformatics and Health care',  ICMR workshop " Harnessing the power of oncology data analytics for early diagnosis and treatment" 15th February - 16th February 2018

Title
Tutorial
Description

Problems with Partially Observed (Incomplete) Networks: Biases, Skewed Results, and Solutions (with Tina Eliassi-Rad and   Sucheta Soundarajan ) [SIAM SDM 2018] Abstract, Slides, and Resources

Secondary Department

Recent Publications

Timothy LaRock, Timothy Sakharov, Sahely Bhadra, Tina Eliassi-Rad:
Applied Network Science 5 (1) 60 (2020)
Viivi Uurtio , Sahely Bhadra and Juho Rousu
Proceedings of the 36th International Conference on Machine Learning(ICML) 6383--6391 (2019)
Anish Mathew, Deepak P and Sahely Bhadra
ICML 2019 Time Series Workshop (2019)
Sahely Bhadra
P D., Jurek-Loughrey A. (eds) Linking and Mining Heterogeneous and Multi-view Data. Unsupervised and Semi-Supervised Learning. Springer, Cham 1-25 (2019)
Viivi Uurtio, Sahely Bhadra, Juho Rusu
IEEE International Conference on Data Mining (ICDM'18) (2018)