Romila Pradhan
Computer Science · Purdue University West Lafayette
Publications
21
Citations
125
Est. group size
—
Recurring co-author estimate
Active years
12
Publishing since 2015
Romila Pradhan works on making machine learning systems more transparent and trustworthy, particularly by generating human-understandable explanations for why models make certain predictions, including cases involving unfairness or bias. Their research also touches on data quality issues, such as how to select or acquire good training data and how to handle changes in data over time (data drift). This work sits at the intersection of database systems and machine learning, often published in data management venues.
Publication output has been variable but persistent over the last decade, with a gap in 2019-2020, a resurgence from 2021-2022, and continued output through 2024-2026, averaging about 2 papers per year in the last five years.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Selective Data Expansion for Model Performance
OpenProceedings · 2026
- Explanations for Machine Learning Pipelines under Data Drift
2025
- SourceSplice: Source Selection for Machine Learning Tasks
arXiv (Cornell University) · 2025
- Explanations for Machine Learning Pipelines under Data Drift
2025
- Example-based Explanations for Random Forests using Machine Unlearning
arXiv (Cornell University) · 2024
- Data Acquisition for Improving Model Fairness using Reinforcement Learning
arXiv (Cornell University) · 2024
- Interpretable Data-Based Explanations for Fairness Debugging
Proceedings of the 2022 International Conference on Management of Data · 2022
- Explainable AI: Foundations, Applications, Opportunities for Data Management Research
Proceedings of the 2022 International Conference on Management of Data · 2022
- Explainable AI: Foundations, Applications, Opportunities for Data Management Research
2022 IEEE 38th International Conference on Data Engineering (ICDE) · 2022
- Generating Interpretable Data-Based Explanations for Fairness Debugging using Gopher
Proceedings of the 2022 International Conference on Management of Data · 2022
- Demonstration of generating explanations for black-box algorithms using Lewis
Proceedings of the VLDB Endowment · 2021
- Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals
2021
- Interpretable Data-Based Explanations for Fairness Debugging
arXiv (Cornell University) · 2021
- Explaining Black-Box Algorithms Using Probabilistic Contrastive\n Counterfactuals
arXiv (Cornell University) · 2021
- Guided Data Fusion
2018
- arXiv (Cornell University)×5
- Proceedings of the 2022 International Conference on Management of Data×3
- Lecture notes in computer science×2
- Proceedings of the VLDB Endowment×1
- 2022 IEEE 38th International Conference on Data Engineering (ICDE)×1
- Qiuling Xu
Computer Science · Purdue University West Lafayette
- Guanhong Tao
Computer Science · Indiana University
- Guangyu Shen
Computer Science · Purdue University West Lafayette
- Di Tang
Computer Science · Indiana University
- Hanxi Guo
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile