Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search
Summary: Auto-Pipeline synthesizes multi-step data-cleaning pipelines from input tables and a target schema, rather than examples. It exploits implicit constraints (FDs, keys) to guide reinforcement learning and search, recovering ~70% of real pipelines up to 10 steps. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Junwen Yang (University of Chicago)
- 2. Yeye He (Microsoft)
- 3. Surajit Chaudhuri (Microsoft)
BibTeX Citation
@article{yang_vldb21,
title = {{Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search}},
author = {Yang, Junwen and He, Yeye and Chaudhuri, Surajit},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {11},
pages = {2563--2575},
doi = {10.14778/3476249.3476303},
url = {https://doi.org/10.14778/3476249.3476303},
year = {2021}
}
Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,990 | Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V | 2023 | VLDB | 6.4105738e-05 |
| 5,403 | Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples | 2023 | VLDB | 6.2306083e-05 |
| 8,177 | HAIPipe: Combining Human-generated and Machine-generated Pipelines for Data Preparation | 2023 | SIGMOD | 5.4730821e-05 |
| 8,797 | Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representations | 2024 | SIGMOD | 5.3702298e-05 |
| 9,380 | Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence | 2025 | VLDB | 5.2755515e-05 |
| 10,202 | BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,457 | FlowPilot: A Suggestion System for Designing Scientific Workflows | 2026 | SIGMOD | 5.093636e-05 |
| 11,309 | LucidScript: Bottom-up Standardization for Data Preparation | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,980 | Auto-Join: Joining Tables by Leveraging Transformations | 2017 | VLDB |
| 2 | 5,901 | A Scalable AutoML Approach Based on Graph Neural Networks | 2022 | VLDB |
| 3 | 4,412 | Auto-Transform: Learning-to-Transform by Patterns | 2020 | VLDB |
| 4 | 2,744 | Auto-Suggest: Learning-to-Recommend Data Preparation Steps Using Data Science Notebooks | 2020 | SIGMOD |
| 5 | 9,629 | Auto-BI: Automatically Build BI-Models Leveraging Local Join Prediction and Global Schema Graph | 2023 | VLDB |
| 6 | 8,914 | CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning | 2024 | SIGMOD |
| 7 | 6,074 | Automatic Data Acquisition for Deep Learning | 2021 | VLDB |
| 8 | 8,177 | HAIPipe: Combining Human-generated and Machine-generated Pipelines for Data Preparation | 2023 | SIGMOD |
| 9 | 9,380 | Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence | 2025 | VLDB |
| 10 | 5,403 | Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples | 2023 | VLDB |