Autocross: Automatic feature crossing for tabular data in real-world applications

Yuanfei Luo; Quanming Yao; Mengshuo Wang; Wei Wei Tu; Hao Zhou; Yuqiang Chen; Wenyuan Dai; Qiang Yang

doi:10.1145/3292500.3330679

Autocross: Automatic feature crossing for tabular data in real-world applications

Yuanfei Luo, Quanming Yao^*, Mengshuo Wang, Wei Wei Tu, Hao Zhou, Yuqiang Chen, Wenyuan Dai, Qiang Yang

^*Corresponding author for this work

Department of Computer Science and Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

81 Citations (Scopus)

Abstract

Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its customers, ranging from banks, hospitals, to Internet corporations. By performing beam search in a tree-structured space, AutoCross enables efficient generation of high-order cross features, which is not yet visited by existing works. Additionally, we propose successive mini-batch gradient descent and multi-granularity discretization to further improve efficiency and effectiveness, while ensuring simplicity so that no machine learning expertise or tedious hyper-parameter tuning is required. Furthermore, the algorithms are designed to reduce the computational, transmitting, and storage costs involved in distributed computing. Experimental results on both benchmark and real-world business datasets demonstrate the effectiveness and efficiency of AutoCross. It is shown that AutoCross can significantly enhance the performance of both linear and deep models.¹

Original language	English
Title of host publication	KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	1936-1945
Number of pages	10
ISBN (Electronic)	9781450362016
DOIs	https://doi.org/10.1145/3292500.3330679
Publication status	Published - 25 Jul 2019
Event	25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019 - Anchorage, United States Duration: 4 Aug 2019 → 8 Aug 2019

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019
Country/Territory	United States
City	Anchorage
Period	4/08/19 → 8/08/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computing Machinery.

Keywords

AutoML
Feature Crossing
Tabular Data

Access to Document

10.1145/3292500.3330679

Cite this

Luo, Y., Yao, Q., Wang, M., Tu, W. W., Zhou, H., Chen, Y., Dai, W., & Yang, Q. (2019). Autocross: Automatic feature crossing for tabular data in real-world applications. In KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1936-1945). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/3292500.3330679

Luo, Yuanfei ; Yao, Quanming ; Wang, Mengshuo et al. / Autocross : Automatic feature crossing for tabular data in real-world applications. KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2019. pp. 1936-1945 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{44b6fe7e16e6460fbc8b806c0e46db3d,

title = "Autocross: Automatic feature crossing for tabular data in real-world applications",

abstract = "Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its customers, ranging from banks, hospitals, to Internet corporations. By performing beam search in a tree-structured space, AutoCross enables efficient generation of high-order cross features, which is not yet visited by existing works. Additionally, we propose successive mini-batch gradient descent and multi-granularity discretization to further improve efficiency and effectiveness, while ensuring simplicity so that no machine learning expertise or tedious hyper-parameter tuning is required. Furthermore, the algorithms are designed to reduce the computational, transmitting, and storage costs involved in distributed computing. Experimental results on both benchmark and real-world business datasets demonstrate the effectiveness and efficiency of AutoCross. It is shown that AutoCross can significantly enhance the performance of both linear and deep models.1",

keywords = "AutoML, Feature Crossing, Tabular Data",

author = "Yuanfei Luo and Quanming Yao and Mengshuo Wang and Tu, \{Wei Wei\} and Hao Zhou and Yuqiang Chen and Wenyuan Dai and Qiang Yang",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019 ; Conference date: 04-08-2019 Through 08-08-2019",

year = "2019",

month = jul,

day = "25",

doi = "10.1145/3292500.3330679",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery",

pages = "1936--1945",

booktitle = "KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

}

Luo, Y, Yao, Q, Wang, M, Tu, WW, Zhou, H, Chen, Y, Dai, W & Yang, Q 2019, Autocross: Automatic feature crossing for tabular data in real-world applications. in KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, pp. 1936-1945, 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019, Anchorage, United States, 4/08/19. https://doi.org/10.1145/3292500.3330679

Autocross: Automatic feature crossing for tabular data in real-world applications. / Luo, Yuanfei; Yao, Quanming; Wang, Mengshuo et al.
KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2019. p. 1936-1945 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Autocross

T2 - 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2019

AU - Luo, Yuanfei

AU - Yao, Quanming

AU - Wang, Mengshuo

AU - Tu, Wei Wei

AU - Zhou, Hao

AU - Chen, Yuqiang

AU - Dai, Wenyuan

AU - Yang, Qiang

PY - 2019/7/25

Y1 - 2019/7/25

N2 - Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its customers, ranging from banks, hospitals, to Internet corporations. By performing beam search in a tree-structured space, AutoCross enables efficient generation of high-order cross features, which is not yet visited by existing works. Additionally, we propose successive mini-batch gradient descent and multi-granularity discretization to further improve efficiency and effectiveness, while ensuring simplicity so that no machine learning expertise or tedious hyper-parameter tuning is required. Furthermore, the algorithms are designed to reduce the computational, transmitting, and storage costs involved in distributed computing. Experimental results on both benchmark and real-world business datasets demonstrate the effectiveness and efficiency of AutoCross. It is shown that AutoCross can significantly enhance the performance of both linear and deep models.1

AB - Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its customers, ranging from banks, hospitals, to Internet corporations. By performing beam search in a tree-structured space, AutoCross enables efficient generation of high-order cross features, which is not yet visited by existing works. Additionally, we propose successive mini-batch gradient descent and multi-granularity discretization to further improve efficiency and effectiveness, while ensuring simplicity so that no machine learning expertise or tedious hyper-parameter tuning is required. Furthermore, the algorithms are designed to reduce the computational, transmitting, and storage costs involved in distributed computing. Experimental results on both benchmark and real-world business datasets demonstrate the effectiveness and efficiency of AutoCross. It is shown that AutoCross can significantly enhance the performance of both linear and deep models.1

KW - AutoML

KW - Feature Crossing

KW - Tabular Data

UR - https://www.scopus.com/pages/publications/85071171356

U2 - 10.1145/3292500.3330679

DO - 10.1145/3292500.3330679

M3 - Conference Paper published in a book

AN - SCOPUS:85071171356

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 1936

EP - 1945

BT - KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

Y2 - 4 August 2019 through 8 August 2019

ER -

Luo Y, Yao Q, Wang M, Tu WW, Zhou H, Chen Y et al. Autocross: Automatic feature crossing for tabular data in real-world applications. In KDD 2019 - Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2019. p. 1936-1945. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3292500.3330679

Autocross: Automatic feature crossing for tabular data in real-world applications

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this