Aditya Sinha
Scholar

Aditya Sinha

Google Scholar ID: 5letoXIAAAAJ
Netflix Research, University of Illinois, Urbana-Champaign
Machine LearningRepresentation LearningGraph Theory
Citations & Impact
All-time
Citations
411
 
H-index
6
 
i10-index
5
 
Publications
15
 
Co-authors
22
list available
Publications
15 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • 2024: Paper 'HypStructure' accepted to NeurIPS '24.
  • 2022: Two papers accepted to NeurIPS '22; presented work in New Orleans.
  • 2022: Work on efficient GCN training published as a poster at ICLR '22.
  • 2022: Node-level differentially private GNNs selected as one of four oral presentations at PAIR2Struct Workshop, ICLR '22.
  • 2022: Collaborative paper with University of Washington and Google Research on efficient representations for adaptive deployment posted on arXiv.
  • June 2022: Patent application filed for scalable self-supervised graph clustering.
  • Served as reviewer for top-tier conferences: NeurIPS (2021, 2024), ICML (2022, 2024), ICLR (2025), AAAI (2025).
  • April 2022: Presented IGLU at ICLR '22.
Research Experience
  • Currently a Research Scientist at Netflix Research, Foundation Models and Inference Research group.
  • Research Scientist Intern at Netflix Research (Summer 2023).
  • Contract Research Engineer at Google Research India, collaborating with Dr. Gaurav Aggarwal (M2U2 Group) and Dr. Prateek Jain (MLO Group) on differential privacy, large-scale graph representation learning, adaptive deployment, and automated hyperparameter tuning.
  • Research Fellow at Microsoft Research India for one year, working with Dr. Prateek Jain, Prof. Purushottam Kar, and Dr. Sundararajan Sellamanickam on efficient training of Graph Convolutional Networks, and with Dr. Ayush Choure on positional click bias estimation and mitigation in search.
  • Completed undergraduate thesis at Microsoft Research India with Dr. Prateek Jain and Dr. Ayush Choure on scalable algorithms for leveraging social network graphs in recommendation systems.