Romila Pradhan

Romila Pradhan

Assistant Professor • Purdue University
Computer & Information Technology



ABOUT

I am an Assistant Professor at Purdue University in the Department of Computer and Information Technology, and a faculty affiliate at the Center for Education and Research in Information Assurance and Security (CERIAS).

Previously, I was a Postdoctoral Researcher at the Halıcıoğlu Data Science Institute in the University of California San Diego, and a Visiting Assistant Professor in the Department of Computer Science at Purdue University. I earned my Ph.D. in Computer Science from Purdue University and graduated with M.S. and B.S. in Mathematics and Computing from the Indian Institute of Technology (IIT) Kharagpur, India.

My research is supported by an NSF CAREER Award, a CASMI research grant, and a Google Research Scholar Award.

RESEARCH INTERESTS

I study problems at the intersection of data management and machine learning. My research is driven by the need to build trustworthy and responsible decision-making systems.

My current research is in the area of responsible data science, aimed at developing systems that enable explainability, fairness, and accountability of data-driven decision-making systems. Previously, I have worked on problems in data integration, focusing on resolving conflicts in data integrated from disparate data sources and ensuring end-users can trust the quality of the integrated data.

I am always looking for PhD students to collaborate with. If you are interested in data management or responsible data analytics, feel free to contact me with your CV/resume and a couple of sentences describing your research interests, and consider applying to Purdue CIT!

NEWS

6/23 Excited to receive an NSF CAREER Award
3/23 Gave a talk on fairness debugging using Gopher at MIT CSAIL's Causality reading group
11/22 Delighted to receive funding from the Center for Advancing Safety of Machine Intelligence (CASMI) for building safe, equitable, and beneficial AI systems
10/22 Position paper with Tianyi Li on human-in-the-loop bias mitigation in data science accepted to the Human-Centered AI Workshop at NeurIPS 2022
6/22 Presented our paper on debugging fairness of machine learning models (Gopher) at SIGMOD 22
6/22 & 5/22 Gave tutorial on Explainable AI and Opportunities for Data Management Research at SIGMOD 22 and ICDE 22
4/22 Honored to receive a Google Research Scholar Award! Thanks, Google!
... more

PUBLICATIONS

Human-in-the-Loop Bias Mitigation in Data Science
Romila Pradhan, Tianyi Li
Human-Centered AI Workshop (HCAI) @ NeurIPS 22 (Vision)

Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher
Jiongli Zhu, Romila Pradhan, Boris Glavic, Babak Salimi
SIGMOD 22 ACM International Conference on Management of Data (Demonstration)

Explainable AI: Foundations, Applications, Opportunities for Data Management Research
Romila Pradhan, Aditya Lahiri, Sainyam Galhotra, Babak Salimi
SIGMOD 22 ACM International Conference on Management of Data
(Tutorial Website)

Explainable AI: Foundations, Applications, Opportunities for Data Management Research
Romila Pradhan, Aditya Lahiri, Sainyam Galhotra, Babak Salimi
ICDE 22 IEEE International Conference on Data Engineering
(Tutorial Website)

Interpretable Data-Based Explanations for Fairness Debugging
Romila Pradhan, Jiongli Zhu, Boris Glavic, Babak Salimi
SIGMOD 22 ACM International Conference on Management of Data
(Project Website)

Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals
Sainyam Galhotra*, Romila Pradhan*, Babak Salimi
SIGMOD 21 ACM International Conference on Management of Data
(Project Website)

Feature Attribution and Recourse via Probabilistic Contrastive Counterfactuals
Sainyam Galhotra, Romila Pradhan, Babak Salimi
ICML Algorithmic Recourse Workshop 21 International Conference on Machine Learning

Demonstration of Generating Explanations for Black-Box Algorithms Using Lewis
Paul Y. Wang, Sainyam Galhotra, Romila Pradhan, Babak Salimi
VLDB 21 Proceedings of the VLDB Endowment (Demonstration)

AuthIntegrate: Toward Combating False Data on the Internet
Romila Pradhan, Sunil Prabhakar
KDD 19 Workshop on Truth Discovery and Fact Checking: Theory and Practice ACM SIGKDD Conference on Knowledge Discovery and Data Mining

Guided Data Fusion
PhD Thesis, Purdue University, 18

Leveraging Data Relationships to Resolve Conflicts from Disparate Data Sources
Romila Pradhan, Walid G. Aref, Sunil Prabhakar
DEXA 18 International Conference on Database and Expert Systems Applications

A Framework to Integrate User Feedback for Rapid Conflict Resolution
Romila Pradhan, Siarhei Bykau, Sunil Prabhakar
ICDE 18 IEEE International Conference on Data Engineering (Demonstration)

Staging User Feedback toward Rapid Conflict Resolution in Data Fusion
Romila Pradhan, Siarhei Bykau, Sunil Prabhakar
SIGMOD 17 ACM International Conference on Management of Data

RESEARCH GROUP

I have been fortunate to work with the following graduate and undergraduate students:

Tejendra Pratap Singh (MS, Purdue CIT, Spring 2023--)
Shashank Thandri (MS, Purdue CIT, Spring 2023--)
Sathvika Kotha (MS, Purdue CIT, Fall 2022--)
Ekta (MS, Purdue CIT, Fall 2022--)
Tanmay Surve (MS, Purdue CIT, Spring 2022--)
Ahana Bhattacharyya (BS, SUNY Buffalo CS, Spring 2023--)
Liming Liu (BS, Purdue CIT, Spring 2023)
Anusha Sarraf (BS, Purdue CS, Spring 2023)
Manas Paranjape (BS, Purdue CS, Fall 2022)

TEACHING

CNIT 58100-RDM: Responsible Data Management. Spring 23, Fall 22
CNIT 48700: Database Administration. Fall 22, Fall 21
CNIT 39200: Enterprise Data Management. Spring 22

SERVICE

Program Committee Member
24 EDBT
23 SIGKDD, ICDE PhD Symposium, FAccT, SSS, CIKM (Demo track)
22 SIGMOD, SIGKDD, EDBT, CIKM (Short Paper Track)

Journal Reviewing
22 The VLDB Journal
22, 21 TKDE
19 TDSC

External Reviewer
22 PODS
21 VLDB , ICDE
20 CIKM
19 ICDE, The Web Conference
11-16 SIGMOD, EDBT, ICDE, CIKM

Proposal Review
22, 23 NSF