Applied Scientist at Amazon A9
Pronouns: she/herSince May 2020, I’m an Applied Scientist at Amazon. I help innovate, develop, evaluate, and launch deep-learned models to fuel next-generation Amazon Search, with a focus on improving search quality in new and emerging locales.
I received my Ph.D. in Computer Science from Carnegie Mellon University, where I was advised by Prof. Christos Faloutsos and supported partially by the Snap Graduate Fellowship. My thesis focused on anomaly detection and semi-supervised learning in graphs. Prior to that, I received my B.Tech. (Hons.) in Computer Science and Engineering from Indian Institute of Technology Madras in 2015.
Outside of work, I like to run, play board games, solve puzzles, read, and travel. I am also learning kathak, a North Indian classical dance. I can be bribed with a good chai tea latte, some spicy biriyani, and a basundhi.
My CV is here.
On How People Navigate Through Their Personal Web of Things
Dhivya Eswaran, Shamsi Iqbal, Adam Fourney, Shane Williams, Paul Bennett
CHI 2020 Workshop on Speculative Designs for Emergent Personal Data Trails: Signs, Signals and Signifiers
[paper]
Higher-Order Label Homogeneity and Spreading in Graphs
Dhivya Eswaran, Srijan Kumar, Christos Faloutsos
The Web Conference 2020
[paper] [code]
Intervention-Aware Early Warning
Dhivya Eswaran, Christos Faloutsos, Nina Mishra, Yonatan Naamad
IEEE International Conference on Data Mining 2019
[paper] [supplementary]
SedanSpot: Detecting Anomalies in Edge Streams
Dhivya Eswaran, Christos Faloutsos
IEEE International Conference on Data Mining 2018
[paper] [supplementary] [code]
ChangeDAR: Online Localized Change Detection for Sensor Data on a Graph
Bryan Hooi, Leman Akoglu, Dhivya Eswaran, Amritanshu Pandey, Marko Jereminov, Larry Pileggi, Christos Faloutsos
ACM International Conference on Information and Knowledge Management 2018
[paper]
Social-Affiliation Graphs: Patterns and the SOAR Model
Dhivya Eswaran, Reihaneh Rabbany, Artur Dubrawski, Christos Faloutsos
Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2018
[paper] [code]
GridWatch: Sensor Placement and Anomaly Detection in the Electrical Grid
Bryan Hooi, Dhivya Eswaran, Hyun Ah Song, Amritanshu Pandey, Marko Jereminov, Larry Pileggi, Christos Faloutsos
Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2018
[paper] [code]
Beyond Anomaly Detection: LookOut for Pictorial Explanation
Nikhil Gupta, Dhivya Eswaran, Neil Shah, Leman Akoglu, Christos Faloutsos
Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2018
[paper] [code]
SpotLight: Detecting Anomalies in Streaming Graphs
Dhivya Eswaran, Christos Faloutsos, Sudipto Guha, Nina Mishra
ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2018
[paper] [video]
Beyond Assortativity: Proclivity Index for Attributed Networks
Reihaneh Rabbany, Dhivya Eswaran, Artur Dubrawski, Christos Faloutsos
Pacific-Asia Conference on Knowledge Discovery and Data Mining 2017
[paper] [code]
ZooBP: Belief Propagation for Heterogeneous Networks
Dhivya Eswaran, Stephan Guennemann, Christos Faloutsos, Disha Makhija, Mohit Kumar
International Conference on Very Large Data Bases 2017
[paper] [code]
Why You Should Charge Your Friends for Borrowing Your Stuff
Kijung Shin, Euiwoong Lee, Dhivya Eswaran, Ariel D. Procaccia
International Joint Conference on Artificial Intelligence 2017
[paper]
The Power of Certainty: A Dirichlet-Multinomial Model for Belief Propagation
Dhivya Eswaran, Stephan Guennemann, Christos Faloutsos
SIAM International Conference on Data Mining 2017
[paper] [code]
Modeling Website Topic Cohesion at Scale to Improve Webpage Classification
Dhivya Eswaran, Paul N. Bennett, Joseph J. Pfeiffer III
ACM SIGIR Conference on Research and Development in Information Retrieval 2015
[paper]
Towards Creating Pedagogic Views from Encyclopedic Resources
Ditty Mathew, Dhivya Eswaran, Sutanu Chakraborti
NAACL 2015 Workshop on Innovative Use of NLP for Building Educational Applications
[paper]