Research Interests

Wasing the always of wanting of knowing.
The eternal desire of a hungry soul is knowledge.
                                                            – Mistborn Series, Brandon Sanderson

My goal is to develop principled designs and analyses of machine learning (ML) and artificial intelligence (AI) models, particularly those involving graphs, so that they are ethical, scalable, and reliable when deployed in the real world. My research has addressed the following themes:

  • Scalability: Summarization, triangle query processing; Distance estimations; Node classification for graphs with millions of nodes

  • Robustness: Sketching linear classifiers to increase robustness to adversarial attacks; Designing training paradigms for stochastic gradient descent learners in settings of incomplete and noisy information

  • Algorithmic Fairness: Quantifying tradeoffs between accuracy and bias of graph neural networks for node classification; Spectral graph partitioning for fair and balanced clusters

  • Trust: Crowdsourcing the veracity of news articles and facilitating trustworthiness amongst users through incentives, gamification, and digital signalling


January 2019 – Present
University of Helsinki

Graduate Research Assistant

with Michael Mathioudakis

Responsibilities include

  • Developing theory, algorithms, and applications of low-dimensional representations of graphs, specifically focusing on node embeddings.
  • Conducted analyses on node classification, summarization, and graph property estimation.
  • Designed large-scale experiments on graphs with millions of nodes from social, communication, web, and biological network domains.
July 2021 – November 2021
UPF Barcelona

Doctoral Intern

with Carlos Castillo

Responsibilities include

  • Quantifying the tradeoffs between algorithmic fairness and accuracy of graph neural networks in the context of node classification.
  • Designed pre-training and post-training interventions to reduce algorithmic bias.
March 2018 – November 2018

Research Associate

with Ponnurangam Kumaraguru

Responsibilities include

  • Studied the role of game elements such as badges and reputation points in characterizing underlying social qualities like popularity and impact of users on Stack Overflow.
  • Applied statistical learning, and time-series analysis methods to empirically quantify and validate the strength of game elements/digital signals on a rich dataset of 3,831,147 users and their activities spanning over a decade.
  • Analyzed the presence of costly to earn and hard to observe signals to qualitatively differen-tiate between highly impactful and highly popular users.
August 2017 – February 2018

Visiting Research Scholar

with Adish Singla

Responsibilities include

  • Designing novel, state-of-the-art algorithms for teaching a classroom of online projected gradient-descent learners with provable guarantees under complete and incomplete information paradigms.
  • Studied applications of machine teaching methods on synthetic and real-world data for binary classification and handwriting improvement tasks.
  • Developed Bayesian inference algorithms for detecting fake news in social networks and jointly learning users’ flagging accuracy over time.
August 2016 – June 2017

Junior Research Fellow

with Anirban Dasgupta

Responsibilities include

  • Designed versatile algorithms and novel, unbiased estimators for degree distribution and degree-wise clustering coefficients of large graphs.
  • Conducted experimental evaluations on public network datasets to obtain close estimates of the actual values, for storage less than 1% of the input graph size.
May 2016 – July 2016

Google Summer of Code (GSoC) Intern

with Johan Rosenkilde and David Lucas

Responsibilities include

  • Designed computationally efficient methods for atomic representations of elements of skew polynomial rings and for answering basic questions about them.
  • Implemented methods for computing combinatorial properties, and for encoding and decoding algorithms for Golay, Gabidulin and Rank-Metric Codes.
May 2013 – July 2013
TIFR, India

Undergraduate Research Intern

with Prahladh Harsha

Responsibilities include

  • Analyzed randomized variants of the deterministic multiple weights update algorithm to show that the total expected cost is only slightly worse than the best possible strategy in hindsight.
  • Surveyed its application to the multi-commodity packing flows problem and a high quality approximation efficiently with provable guarantees.