Towards Benchmarking Feature Type Inference for AutoML Platforms

Summary: First benchmark for ML-driven feature type inference in AutoML; presents a 9,921-sample, 9-class labeled dataset to standardize evaluation. ML-based typing yields 14% avg lift (up to 38%), beats industrial tools on 47/60 downstream models, and the dataset, models, and leaderboards are publicly released. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6166
Venue: SIGMOD
Year: 2021
Pagerank: 5.6021738e-05
Overall Rank: 5,244 | 63.56%
DOI: 10.1145/3448016.3457274

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
3,938	SimpleTS: An Efficient and Universal Model Selection Framework for Time Series Forecasting	2023	VLDB	6.6111703e-05
5,283	Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V	2023	VLDB	5.5843052e-05
5,929	SchemaPile: A Large Collection of Relational Database Schemas	2024	SIGMOD	5.2635297e-05
6,552	How do Categorical Duplicates Affect ML? A New Benchmark and Empirical Analyses	2024	VLDB	5.0109216e-05
7,810	Pollock: A Data Loading Benchmark	2023	VLDB	4.6415099e-05
8,125	Automation of Data Prep, ML, and Data Science: New Cure or Snake Oil?	2021	SIGMOD	4.5765541e-05
8,515	UPLIFT: Parallelization Strategies for Feature Transformations in Machine Learning Workloads	2022	VLDB	4.4901466e-05
9,355	GIO: Generating Efficient Matrix and Frame Readers for Custom Data Formats by Example	2023	SIGMOD	4.3484264e-05
10,636	CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines	2025	VLDB	4.1905499e-05

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
252	Snorkel: Rapid Training Data Creation with Weak Supervision	2018	VLDB	0.00030532082
1,218	Snuba: Automating Weak Supervision to Label Training Data	2019	VLDB	0.00013221309
1,481	Automating Large-Scale Data Quality Verification	2018	VLDB	0.00011715754
3,483	Transform-Data-by-Example (TDE): An Extensible Search Engine for Data Transformations	2018	VLDB	7.0493668e-05
4,197	Overton: A Data System for Monitoring and Improving Machine-Learned Products	2020	CIDR	6.3625568e-05
4,746	Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models	2021	SIGMOD	5.9446518e-05
5,930	ActiveClean: An Interactive Data Cleaning Framework For Modern Machine Learning	2016	SIGMOD	5.2632185e-05
6,411	Synthesizing Type-Detection Logic for Rich Semantic Data Types using Open-source Code	2018	SIGMOD	5.0675656e-05
7,818	Foofah: A Programming-By-Example System for Synthesizing Data Transformation Programs	2017	SIGMOD	4.6398687e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
6,345	A Relational Framework for Classifier Engineering	2017	PODS	5.0970607e-05
10,521	Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables	2025	SIGMOD	4.1905499e-05
11,207	Steered Training Data Generation for Learned Semantic Type Detection	2023	SIGMOD	4.1905499e-05
5,306	A Scalable AutoML Approach Based on Graph Neural Networks	2022	VLDB	5.5725759e-05
6,411	Synthesizing Type-Detection Logic for Rich Semantic Data Types using Open-source Code	2018	SIGMOD	5.0675656e-05
9,372	FEBench: A Benchmark for Real-Time Relational Data Feature Extraction	2023	VLDB	4.3461481e-05
9,885	Scalable and Usable Relational Learning With Automatic Language Bias	2021	SIGMOD	4.2580321e-05
6,552	How do Categorical Duplicates Affect ML? A New Benchmark and Empirical Analyses	2024	VLDB	5.0109216e-05
7,419	MLBench: Benchmarking Machine Learning Services Against Human Experts	2018	VLDB	4.7302312e-05
5,098	ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models	2024	VLDB	5.6943033e-05