Visus: An interactive system for automatic machine learning model building and curation

Aecio Santos; Sonia Castelo; Cristian Felix; Jorge Piazentin Ono; Bowen Yu; Sungsoo Hong; Claudio T. Silva; Enrico Bertini; Juliana Freire

doi:10.1145/3328519.3329134

Visus: An interactive system for automatic machine learning model building and curation

Aecio Santos, Sonia Castelo, Cristian Felix, Jorge Piazentin Ono, Bowen Yu, Sungsoo Hong, Claudio T. Silva, Enrico Bertini, Juliana Freire

Urban Initiative

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-toend ML data processing pipelines. However, these follow a besteffort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.

Original language	English (US)
Title of host publication	Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450367912
DOIs	https://doi.org/10.1145/3328519.3329134
State	Published - Jul 5 2019
Event	2019 Workshop on Human-In-the-Loop Data Analytics, HILDA 2019, co-located with SIGMOD 2019 - Amsterdam, Netherlands Duration: Jul 5 2019 → …

Publication series

Name	Proceedings of the ACM SIGMOD International Conference on Management of Data
ISSN (Print)	0730-8078

Conference

Conference	2019 Workshop on Human-In-the-Loop Data Analytics, HILDA 2019, co-located with SIGMOD 2019
Country/Territory	Netherlands
City	Amsterdam
Period	7/5/19 → …

Keywords

Automatic machine learning
Data analytics
Data visualization

ASJC Scopus subject areas

Software
Information Systems

Access to Document

10.1145/3328519.3329134

Cite this

Santos, A., Castelo, S., Felix, C., Ono, J. P., Yu, B., Hong, S., Silva, C. T., Bertini, E., & Freire, J. (2019). Visus: An interactive system for automatic machine learning model building and curation. In Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019 Article a6 (Proceedings of the ACM SIGMOD International Conference on Management of Data). Association for Computing Machinery. https://doi.org/10.1145/3328519.3329134

Visus: An interactive system for automatic machine learning model building and curation. / Santos, Aecio; Castelo, Sonia; Felix, Cristian et al.
Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019. Association for Computing Machinery, 2019. a6 (Proceedings of the ACM SIGMOD International Conference on Management of Data).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Santos, A, Castelo, S, Felix, C, Ono, JP, Yu, B, Hong, S, Silva, CT, Bertini, E & Freire, J 2019, Visus: An interactive system for automatic machine learning model building and curation. in Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019., a6, Proceedings of the ACM SIGMOD International Conference on Management of Data, Association for Computing Machinery, 2019 Workshop on Human-In-the-Loop Data Analytics, HILDA 2019, co-located with SIGMOD 2019, Amsterdam, Netherlands, 7/5/19. https://doi.org/10.1145/3328519.3329134

Santos A, Castelo S, Felix C, Ono JP, Yu B, Hong S et al. Visus: An interactive system for automatic machine learning model building and curation. In Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019. Association for Computing Machinery. 2019. a6. (Proceedings of the ACM SIGMOD International Conference on Management of Data). doi: 10.1145/3328519.3329134

@inproceedings{a23f3fd6d91244e9a665a3f3f4d8f378,

title = "Visus: An interactive system for automatic machine learning model building and curation",

abstract = "While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-toend ML data processing pipelines. However, these follow a besteffort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.",

keywords = "Automatic machine learning, Data analytics, Data visualization",

author = "Aecio Santos and Sonia Castelo and Cristian Felix and Ono, {Jorge Piazentin} and Bowen Yu and Sungsoo Hong and Silva, {Claudio T.} and Enrico Bertini and Juliana Freire",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 2019 Workshop on Human-In-the-Loop Data Analytics, HILDA 2019, co-located with SIGMOD 2019 ; Conference date: 05-07-2019",

year = "2019",

month = jul,

day = "5",

doi = "10.1145/3328519.3329134",

language = "English (US)",

series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019",

}

TY - GEN

T1 - Visus

T2 - 2019 Workshop on Human-In-the-Loop Data Analytics, HILDA 2019, co-located with SIGMOD 2019

AU - Santos, Aecio

AU - Castelo, Sonia

AU - Felix, Cristian

AU - Ono, Jorge Piazentin

AU - Yu, Bowen

AU - Hong, Sungsoo

AU - Silva, Claudio T.

AU - Bertini, Enrico

AU - Freire, Juliana

PY - 2019/7/5

Y1 - 2019/7/5

N2 - While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-toend ML data processing pipelines. However, these follow a besteffort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.

AB - While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) approaches have been proposed that help with this problem by synthesizing end-toend ML data processing pipelines. However, these follow a besteffort approach and a user in the loop is necessary to curate and refine the derived pipelines. Since domain experts often have little or no expertise in machine learning, easy-to-use interactive interfaces that guide them throughout the model building process are necessary. In this paper, we present Visus, a system designed to support the model building process and curation of ML data processing pipelines generated by AutoML systems. We describe the framework used to ground our design choices and a usage scenario enabled by Visus. Finally, we discuss the feedback received in user testing sessions with domain experts.

KW - Automatic machine learning

KW - Data analytics

KW - Data visualization

UR - http://www.scopus.com/inward/record.url?scp=85072792719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072792719&partnerID=8YFLogxK

U2 - 10.1145/3328519.3329134

DO - 10.1145/3328519.3329134

M3 - Conference contribution

AN - SCOPUS:85072792719

T3 - Proceedings of the ACM SIGMOD International Conference on Management of Data

BT - Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2019

PB - Association for Computing Machinery

Y2 - 5 July 2019

ER -

Visus: An interactive system for automatic machine learning model building and curation

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this