CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines

Summary: CatDB leverages data-catalog metadata to produce dataset-specific instructions that steer LLMs to synthesize end-to-end data-centric ML pipelines (cleaning, augmentation, feature engineering, tuning). Built-in validation and error handling reduce hallucinations and yield AutoML-comparable accuracy with much faster scaling. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: h9222f056925628a0
Venue: VLDB
Year: 2025
Pagerank: 5.1064323e-05
Overall Rank: 9,842 | 34.03%
DOI: 10.14778/3742728.3742754
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Saeed Fathollahzadeh (Concordia University)
2. Essam Mansour (Concordia University)
3. Matthias Boehm (Technical University of Berlin)

BibTeX Citation

@article{fathollahzadeh_vldb25,
        title = {{CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines}},
        author = {Fathollahzadeh, Saeed and Mansour, Essam and Boehm, Matthias},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {8},
        pages = {2639--2652},
        doi = {10.14778/3742728.3742754},
        url = {https://doi.org/10.14778/3742728.3742754},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,397	FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction	2027	SIGMOD	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 21 of 21 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
154	MAD Skills: New Analysis Practices for Big Data	2009	VLDB	0.00028524078
163	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00027456647
323	Can Foundation Models Wrangle Your Data?	2023	VLDB	0.00021022156
460	ActiveClean: Interactive Data Cleaning For Statistical Modeling	2016	VLDB	0.00017836918
512	Goods: Organizing Google's Datasets	2016	SIGMOD	0.00017036842
948	Democratizing Data Science through Interactive Curation of ML Pipelines	2019	SIGMOD	0.00012900728
1,278	Automating Large-Scale Data Quality Verification	2018	VLDB	0.00011208469
1,616	SystemDS: A Declarative Machine Learning System for the End-to-End Data Science Lifecycle	2020	CIDR	0.00010048776
1,744	Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions	2021	VLDB	9.7253583e-05
1,929	SANTOS: Relationship-based Semantic Table Union Search	2023	SIGMOD	9.3458857e-05
3,093	Correlation Sketches for Approximate Join-Correlation Queries	2021	SIGMOD	7.6378811e-05
3,420	Data Profiling – A Tutorial	2017	SIGMOD	7.300051e-05
3,749	Automated Feature Engineering for Algorithmic Fairness	2021	VLDB	7.0348686e-05
4,354	LIMA: Fine-grained Lineage Tracing and Reuse in Machine Learning Systems	2021	SIGMOD	6.6318545e-05
5,117	Towards Benchmarking Feature Type Inference for AutoML Platforms	2021	SIGMOD	6.2551509e-05
5,230	Saga: A Scalable Framework for Optimizing Data Cleaning Pipelines for Machine Learning Applications	2023	SIGMOD	6.2059854e-05
6,044	A Scalable AutoML Approach Based on Graph Neural Networks	2022	VLDB	5.8887644e-05
7,076	How do Categorical Duplicates Affect ML? A New Benchmark and Empirical Analyses	2024	VLDB	5.5909675e-05
8,327	SMARTFEAT: Efficient Feature Construction through Feature-Level Foundation Model Interactions	2024	CIDR	5.3381899e-05
9,634	GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models	2024	SIGMOD	5.1354312e-05
9,934	Searching a Database of Source Codes Using Contextualized Code Search	2020	VLDB	5.0949141e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,692	AutoDDG: Automated Dataset Description Generation using Large Language Models	2026	SIGMOD
2	10,939	DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation	2026	VLDB
3	11,043	Demonstrating GenDB: Instance-Optimized and Customized Query Processing Code Generation via LLM Agents	2026	VLDB
4	9,003	DataLoom: Simplifying Data Loading with LLMs	2024	VLDB
5	4,351	Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs	2024	VLDB
6	6,438	CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning	2024	SIGMOD
7	10,397	FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction	2027	SIGMOD
8	4,729	LLM for Data Management	2024	VLDB
9	11,131	LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning	2026	VLDB
10	13,672	Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines	2025	SIGMOD