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