Noveen Sachdeva
[email protected]

I am a PhD student in the CSE Department at UC San Diego where I am extremely fortunate to be advised by Prof. Julian McAuley.

My (current) research interests in Machine Learning are Data Mining, NLP, Information Retrieval, Causal Inference, and Reinforcement learning (in no particular order).

More specifically, I have previously been working on sequential recommender systems (RecSys '18, ECIR '18, WSDM '19), off-policy learning (KDD '20), NLP (SIGIR '20), and extreme classification (WWW '21).

CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Recent News
  • [Jan '21] Paper w/ Anshul, Sheshansh, Sumeet, Puru, and Manik accepted to WWW '21!
  • [Oct '20] Mentoring a group of three brilliant undergraduates at UC San Diego.
  • [Oct '20] Awarded the Jacobs School of Engineering Fellowship at UC San Diego.
  • Research
    ECLARE: Extreme Classification with Label Graph Correlations
    Anshul Mittal, Noveen Sachdeva, Sheshansh Agrawal, Sumeet Agarwal, Purushottam Kar, Manik Varma
    The Web Conference (WWW), 2021
    Notified, coming soon!
    Off-policy Bandits with Deficient Support
    Noveen Sachdeva, Yi Su, Thorsten Joachims
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020
    ACM / arXiv / Code / BibTeX
    How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
    Noveen Sachdeva, Julian McAuley
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020
    ACM / arXiv / Code / BibTeX
    Sequential Variational Autoencoders for Collaborative Filtering
    Noveen Sachdeva, Giuseppe Manco, Ettore Ritacco, Vikram Pudi
    ACM International Conference on Web Search and Data Mining (WSDM), 2019
    ACM / arXiv / Code / BibTeX
    Attentive Neural Architecture Incorporating Song Features For Music Recommendation
    Noveen Sachdeva, Kartik Gupta, Vikram Pudi
    ACM International Conference on Recommender Systems (RecSys), 2018
    ACM / arXiv / BibTeX
    Explicit Modelling of the Implicit Short Term User Preferences for Music Recommendation
    Kartik Gupta, Noveen Sachdeva, Vikram Pudi
    European Conference on Information Retrieval (ECIR), 2018
    PDF / BibTeX
    Experience
    Microsoft Research
    Research Intern   with   Dr. Manik Varma
    Bengaluru, India   ·   Jan 2020 - Jun 2020

    Worked on building better machine learning algorithms at the million-scale (Extreme Classification). Formulated a scalable, GCN-inspired algorithm which exploits label-label correlation patterns to massively improve tail-label performance. [WWW '21]

    UC San Diego
    Research Assistant   with   Prof. Julian McAuley
    San Diego, CA   ·   Aug 2019 - Oct 2019

    Ascertained a highly relevant problem in existing recommender systems that exploit textual reviews for rating prediction, and generalize it. Wrote a paper about the realized problem and possible fixes under different scenarios. [SIGIR '20]

    Cornell University
    Research Assistant   with   Prof. Thorsten Joachims
    San Diego, CA   ·   Jun 2019 - Jul 2019

    Worked at the intersection of causal inference, counterfactual learning, and reinforcement learning. The project contributed towards making off-policy learning from biased, logged contextual-bandit data more robust. Formalized a novel, highly relevant problem and generalized different existing estimators. [KDD '20]

    PricewaterhouseCoopers LLP (PwC)
    Data Science Intern   with   Data Science & Innovation team
    Tampa, FL (Remote)   ·   Aug 2018 - Nov 2018

    Worked on clause extraction from sensitive legal documents for top clients in the US. Formulated a de-generate pipeline and compared different statistical and deep-learning-based models for the given task. Reduced task time from days to a few hours, enabling PwC to get new clients in the legal sector.

    ICAR-CNR (National Research Council of Italy)
    Research Assistant   with   Dr. Giuseppe Manco
    Cosenza, Italy   ·   May 2018 - Jul 2018

    Majorly worked on building novel and better systems suited for the task of next-item recommendation. Devised a taxonomy of VAE models for collaborative filtering, demonstrating huge gains over the state-of-the-art on real-world datasets. [WSDM '19]

    Google Summer of Code
    Summer Participant   with   ownCloud
    Remote   ·   May 2017 - Aug 2017

    Implemented a JS-library, complete with unit-tests and swagger-documentation, which works both on Node.JS and browser. [Media coverage]

    Education
    UC San Diego
    Ph.D. in Computer Science & Engineering   ·   4.0
    San Diego, CA   ·   2020 - Present
    IIIT Hyderabad
    B.Tech & M.S. (by research) in Computer Science & Engineering   ·   9.75 / 10.0
    Hyderabad, India   ·   2015 - 2020

    Thanks to Jon Barron for the nice template!