Shubham Gupta

PhD Scholar, Computer Science and Engineering, IIT Delhi | VP – Data Science Info Edge

I am pursuing a PhD in Graph Machine Learning at IIT Delhi under the guidance of Prof. Srikanta Bedathur. My research focuses on temporal graph representation learning and generative modeling.

Industry Experience

I lead end-to-end data science strategy and execution across multiple consumer products — owning both model architecture and business outcomes in high-scale, two-sided marketplace environments.

  • Leadership & Platform Thinking: Drive problem framing, experimentation, and deployment across the DS lifecycle (research → production → monitoring), partnering closely with product, engineering, and business teams.
  • Conversational AI & LLMs (Naukri): Currently leading the conversational AI charter — building in-house fine-tuning and LLM infrastructure to unlock enterprise data for job-seekers and recruiters.
  • Matchmaking & Recommendation (Naukri): Built CV–job matching and recommendation systems using learning-to-rank and large-scale retrieval, delivering ~4× recruiter productivity and ~40% lift in applications.
  • Trust & Safety (Jeevansathi): Led spam and misuse intelligence; upgraded early-lifecycle detection to reduce fake complaints by ~50% and bring time-to-detect under 2 hours.
  • Revenue Science & Monetization(Jeevansathi): Architected dynamic pricing and discounting engines driven by lifecycle and intent propensity models, yielding ~12–15% revenue uplift.
  • Engagement & Two-Sided Matching (Jeevansathi): Built reciprocal matching and engagement systems optimizing for acceptance and interaction quality, driving ~100% growth in engagement metrics.

An up-to-date publication list is available on Google Scholar.

News

Jun 3, 2026

Paper accepted in TMLR, last chapter of my thesis. Pheww

NEUTAG: Graph Transformer for Attributed Graphs
Shubham Gupta, Sayan Ranu and Srikanta Bedathur

Selected Publications [full list]

  1. SIGIR
    MINTT: Memory Inductive Transfer for Temporal Graph Neural Networks
    Tanishq Dubey, Sidharth Agarwal, Shubham Gupta, and Srikanta Bedathur
    In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval 2025
    arXiv
  2. LoG
    Generative Modeling of Labeled Graphs Under Data Scarcity
    Sahil Manchanda, Shubham Gupta, Sayan Ranu, and Srikanta Bedathur
    In Proceedings of the Second Learning on Graphs Conference 2024
    arXiv
  3. ICML
    GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets
    Shubham Gupta, Sahil Manchanda, Sayan Ranu, and Srikanta Bedathur
    In Proceedings of the 40th International Conference on Machine Learning 2023
    arXiv Code
  4. AAAI
    TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs
    Shubham Gupta, Sahil Manchanda, Srikanta Bedathur, and Sayan Ranu
    In Proceedings of the AAAI Conference on Artificial Intelligence 2022
    arXiv