Democratizing Data Science through Interactive Curation of ML Pipelines
Summary: Interactive AutoML for scientists via curated ML pipelines. Uses query-optimization, cost-based bandits, and Bayesian optimization to achieve interactive latency and beat expert solutions on unseen data across 300+ datasets. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zeyuan Shang (Massachusetts Institute of Technology)
- 2. Emanuel Zgraggen (Massachusetts Institute of Technology)
- 3. Benedetto Buratti (Brown University)
- 4. Ferdinand Kossmann (Massachusetts Institute of Technology)
- 5. Philipp Eichmann (Brown University)
- 6. Yeounoh Chung (Brown University)
- 7. Carsten Binnig (Brown University; Technical University of Darmstadt)
- 8. Eli Upfal (Brown University)
- 9. Tim Kraska (Massachusetts Institute of Technology)
BibTeX Citation
@inproceedings{shang_sigmod19,
title = {{Democratizing Data Science through Interactive Curation of ML Pipelines}},
author = {Shang, Zeyuan and Zgraggen, Emanuel and Buratti, Benedetto and Kossmann, Ferdinand and Eichmann, Philipp and Chung, Yeounoh and Binnig, Carsten and Upfal, Eli and Kraska, Tim},
series = {{SIGMOD} '19},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3299869.3319863},
url = {https://dl.acm.org/doi/10.1145/3299869.3319863},
year = {2019}
}
Incoming Citations (Sorted by Pagerank)
Showing 27 of 27 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1 | Access Path Selection in a Relational Database Management System | 1979 | SIGMOD | 0.0024089429 |
| 288 | Towards Estimation Error Guarantees for Distinct Values | 2000 | PODS | 0.00022296371 |
| 532 | MLbase: A Distributed Machine-learning System | 2013 | CIDR | 0.00017072641 |
| 986 | Effortless Data Exploration with zenvisage: An Expressive and Interactive Visual Analytics System | 2017 | VLDB | 0.0001281777 |
| 1,392 | Northstar: An Interactive Data Science System | 2018 | VLDB | 0.00010936065 |
| 2,029 | Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads | 2018 | VLDB | 9.2843642e-05 |
| 2,050 | Vizdom: Interactive Analytics through Pen and Touch | 2015 | VLDB | 9.2546631e-05 |
| 2,059 | LINVIEW: Incremental View Maintenance for Complex Analytical Queries | 2014 | SIGMOD | 9.2471145e-05 |
| 5,084 | Querying Without Keyboards | 2013 | CIDR | 6.3692734e-05 |
| 6,693 | GestureQuery: A Multitouch Database Query Interface | 2013 | VLDB | 5.7992988e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 1,756 | SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle | 2020 | CIDR |
| 2 | 13,387 | ML2DAC: Meta-learning to Democratize AutoML for Clustering Analyses | 2023 | SIGMOD |
| 3 | 13,303 | Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines | 2025 | SIGMOD |
| 4 | 11,043 | mlidea: Interactively Improving ML Data Preparation Code via “Shadow Pipelines” | 2025 | VLDB |
| 5 | 2,677 | Explore-by-Example: An Automatic Query Steering Framework for Interactive Data Exploration | 2014 | SIGMOD |
| 6 | 8,134 | DORIAN in action: Assisted Design of Data Science Pipelines | 2022 | VLDB |
| 7 | 5,901 | A Scalable AutoML Approach Based on Graph Neural Networks | 2022 | VLDB |
| 8 | 4,420 | Optimization for Active Learning-based Interactive Database Exploration | 2019 | VLDB |
| 9 | 7,473 | The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development | 2020 | SIGMOD |
| 10 | 11,746 | Active Reinforcement Learning for Data Preparation: Learn2Clean with Human-In-The-Loop | 2020 | CIDR |