Hi!
I'm a graduate student in the Department of Computer Science, University of Illinois at Urbana-Champaign, pursuing a Master's of Science in Computer Science (thesis track).I was previously a Research Engineer (on contract) at Google Research India, working with Dr. Gaurav Aggarwal in the M2U2 Group (Mixed-Mode User Understanding) and Dr. Prateek Jain in the MLO Group (Machine Learning and Optimization). Here, I worked on problems related to Differential Privacy, developing Large Scale algorithms for Graph Representation Learning and Adaptive Deployment, and exploring the possibility of automated hyperparameter tuning.
Before this, I spent an amazing year at Microsoft Research India as a Research Fellow, working with Dr. Prateek Jain, Prof. Purushottam Kar and Dr. Sundararajan Sellamanickam on problems related to Efficient training of Graph Convolutional Networks and with Dr. Ayush Choure on estimation and mitigation of Positional Click Bias in Search.
I also did my undergraduate thesis at Microsoft Research, India with Dr. Prateek Jain and Dr. Ayush Choure, on developing scalable algorithms for using social network graphs in recommendation systems.
I graduated with a B.E. (Hons.) in Computer Science and a MSc. (Hons.) in Economics from BITS Pilani, Goa, India in 2020. During my time there, I worked on conversational agents and related NLP problems with Prof. Ashwin Srinivasan. Apart from spending my time doing fun research, I hold a keen interest in photography, a passion I got to pursue as part of the Department of Photography at BITS.
For more information, you can check out my CV here or reach out to me on my email :)
Updates
| August 2022: | Starting as a graduate student in the Department of Computer Science, University of Illinois at Urbana-Champaign for my M.S. in C.S. degree! |
| June 2022: | Patent application filed for our work on Scalable Self Supervised Graph Clustering! |
| June 2022: | Paper on our work with amazing collaborators from University of Washington and Google Research, developing efficient representations for Adaptive Deployment out on Arxiv now! |
| April 2022: | Presenting our work IGLU at ICLR '22! Do attend! |
| March 2022: | Our work on node-level differentially private graph neural networks was accepted as one of the four Oral papers at PAIR2Struct Workshop at ICLR '22! |
| Feb 2022: | Serving as a reviewer for ICML '22. |
| Jan 2022: | Our work on Efficient training on GCN's via Lazy Updates will appear at ICLR '22 as a Poster! |
| Dec 2021: | Paper on our work at Google Research India, developing Node-level Differentially Private Graph Neural Networks out on Arxiv! |
| Nov 2021: | Volunteering for NeurIPS '21. Looking forward to attending talks virtually! |
| June 2021: | Serving as a reviewer for NeurIPS '21! |
| June 2021: | Joined the Google Research India lab as a Research Engineer (on contract) working with Dr. Gaurav Aggarwal in the M2U2 Group and Dr. Prateek Jain in the MLO Group! |
| Dec 2020: | Working with Dr. Ayush Choure on the exciting problem of Positional Click Bias Estimation in Search! |
| Dec 2020: | Volunteering for NeurIPS '20. Looking forward to attending exciting talks! |
| Aug 2020: | Joined Microsoft Research India as a Research Fellow, working with Dr. Prateek Jain, Prof. Purushottam Kar and Dr. Sundararajan Sellamanickam on efficient training of GCN's! |
| Aug 2020: | Graduated from BITS Pilani Goa with a dual degree in Computer Science and Economics. |
| July 2020: | Paper on my work at MSRI, using graphs in recommendations systems, out on Arxiv! |
| Jul 2019: | I am doing my bachelor's thesis at the Microsoft Research India lab, where I am working with Dr. Prateek Jain and Dr. Ayush Choure! |
| May 2018: | Summer internship at the SSP lab, ECE, IISc where I will be working with Prof. K.V.S. Hari |
Publications
IGLU: Efficient GCN Training via Lazy Updates
, S. Deepak Narayanan*, Prateek Jain, Purushottam, Kar, Sundararajan Sellamanickam
(Poster) Tenth International Conference on Learning Representations, 2022 ,(ICLR) 2022
pdf |
code |
video
Node-Level Differentially Private Graph Neural Networks
Ameya Daigavane, Gagan Madan, , Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain
(Oral) PAIR2Struct Workshop (ICLR) 2022
pdf |
video
S3GC - Scalable Self Supervised Graph Clustering
Devvrit ., , Inderjit Dhillon, Prateek Jain
Under Review at NeurIPS '22
Matryoshka Representations for Adaptive Deployment
Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, , Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham M. Kakade, Prateek Jain, Ali Farhadi
Under Review at NeurIPS '22
pdf
Rich-Item Recommendations for Rich-Users: Exploiting Dynamic and Static Side Information
Amar Budhiraja*, Gaurush Hiranandani*, Darshak Chhatbar, , Navya Yarrabelly, Ayush Choure, Oluwasanmi Koyejo, Prateek Jain
ArXiv:2001.10495, [cs.LG], `20
pdf
Academic Service