Intermittent Human-in-the-Loop Model Selection using Cerebro: A Demonstration

Summary: Intermittent human-in-the-loop model selection to bridge AutoML throughput and expert guidance. Cerebro demonstrates the approach on five real-world DL workloads, delivering a scalable mixed-initiative search over model architectures and hyperparameters. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: ha77aa1086c7be9b8
Venue: VLDB
Year: 2021
Pagerank: 5.1377385e-05
Overall Rank: 9,590 | 35.72%
DOI: 10.14778/3476311.3476320
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Liangde Li (University of California San Diego)
2. Supun Nakandala (University of California San Diego)
3. Arun Kumar (University of California San Diego)

BibTeX Citation

@article{li_vldb21,
        title = {{Intermittent Human-in-the-Loop Model Selection using Cerebro: A Demonstration}},
        author = {Li, Liangde and Nakandala, Supun and Kumar, Arun},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {12},
        pages = {2687--2690},
        doi = {10.14778/3476311.3476320},
        url = {https://doi.org/10.14778/3476311.3476320},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,435	SHiFT: An Efficient, Flexible Search Engine for Transfer Learning	2023	VLDB	5.3161281e-05
13,734	Reimagining Deep Learning Systems Through the Lens of Data Systems	2024	VLDB	-

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
656	Materialization Optimizations for Feature Selection Workloads	2014	SIGMOD	0.00015052106
1,154	Cerebro: A Data System for Optimized Deep Learning Model Selection	2020	VLDB	0.00011762688
1,567	HELIX: Holistic Optimization for Accelerating Iterative Machine Learning	2019	VLDB	0.00010179013
9,175	Cerebro: A Layered Data Platform for Scalable Deep Learning	2021	CIDR	5.2004231e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	6,404	Human-in-the-loop Data Integration	2017	VLDB
2	12,002	Grouped Learning: Group-By Model Selection Workloads	2021	SIGMOD
3	13,872	Demonstration of Krypton: Optimized CNN Inference for Occlusion-based Deep CNN Explanations	2019	VLDB
4	7,064	Human-in-the-loop Outlier Detection	2020	SIGMOD
5	9,629	Model-Parallel Model Selection for Deep Learning Systems	2021	SIGMOD
6	6,173	Automatic Data Acquisition for Deep Learning	2021	VLDB
7	12,179	Personal Insights for Altering Decisions of Tree-based Ensembles over Time	2020	VLDB
8	948	Democratizing Data Science through Interactive Curation of ML Pipelines	2019	SIGMOD
9	9,175	Cerebro: A Layered Data Platform for Scalable Deep Learning	2021	CIDR
10	1,154	Cerebro: A Data System for Optimized Deep Learning Model Selection	2020	VLDB