AutoRec: An Automated Recommender System

Ting Hsiang Wang; Xia Hu; Haifeng Jin; Qingquan Song; Xiaotian Han; Zirui Liu

doi:10.1145/3383313.3411529

AutoRec: An Automated Recommender System

Ting Hsiang Wang, Xia Hu, Haifeng Jin, Qingquan Song, Xiaotian Han, Zirui Liu

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

15 Scopus citations

Abstract

Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec 1 2, an open-source automated machine learning (AutoML) platform extended from the TensorFlow [3] ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models. AutoRec also supports a highly flexible pipeline that accommodates both sparse and dense inputs, rating prediction and click-through rate (CTR) prediction tasks, and an array of recommendation models. Lastly, AutoRec provides a simple, user-friendly API. Experiments conducted on the benchmark datasets reveal AutoRec is reliable and can identify models which resemble the best model without prior knowledge.

Original language	English (US)
Title of host publication	RecSys 2020 - 14th ACM Conference on Recommender Systems
Publisher	Association for Computing Machinery, Inc
Pages	582-584
Number of pages	3
ISBN (Electronic)	9781450375832
DOIs	https://doi.org/10.1145/3383313.3411529
State	Published - Sep 22 2020
Externally published	Yes
Event	14th ACM Conference on Recommender Systems, RecSys 2020 - Virtual, Online, Brazil Duration: Sep 22 2020 → Sep 26 2020

Publication series

Name	RecSys 2020 - 14th ACM Conference on Recommender Systems

Conference

Conference	14th ACM Conference on Recommender Systems, RecSys 2020
Country/Territory	Brazil
City	Virtual, Online
Period	9/22/20 → 9/26/20

Bibliographical note

Publisher Copyright:
© 2020 Owner/Author.

Keywords

Automated Machine Learning
Hyperparameter Tuning
Model Search
Neural Architecture Search
Recommender Systems

Publisher link

10.1145/3383313.3411529

Find It

Find It at U of M Libraries

Cite this

Wang, TH, Hu, X, Jin, H, Song, Q, Han, X & Liu, Z 2020, AutoRec: An Automated Recommender System. in RecSys 2020 - 14th ACM Conference on Recommender Systems. RecSys 2020 - 14th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, pp. 582-584, 14th ACM Conference on Recommender Systems, RecSys 2020, Virtual, Online, Brazil, 9/22/20. https://doi.org/10.1145/3383313.3411529

@inproceedings{8704274e381b43d4bb6f18538a840814,

title = "AutoRec: An Automated Recommender System",

abstract = "Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec 1 2, an open-source automated machine learning (AutoML) platform extended from the TensorFlow [3] ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models. AutoRec also supports a highly flexible pipeline that accommodates both sparse and dense inputs, rating prediction and click-through rate (CTR) prediction tasks, and an array of recommendation models. Lastly, AutoRec provides a simple, user-friendly API. Experiments conducted on the benchmark datasets reveal AutoRec is reliable and can identify models which resemble the best model without prior knowledge.",

keywords = "Automated Machine Learning, Hyperparameter Tuning, Model Search, Neural Architecture Search, Recommender Systems",

author = "Wang, {Ting Hsiang} and Xia Hu and Haifeng Jin and Qingquan Song and Xiaotian Han and Zirui Liu",

note = "Publisher Copyright: {\textcopyright} 2020 Owner/Author.; 14th ACM Conference on Recommender Systems, RecSys 2020 ; Conference date: 22-09-2020 Through 26-09-2020",

year = "2020",

month = sep,

day = "22",

doi = "10.1145/3383313.3411529",

language = "English (US)",

series = "RecSys 2020 - 14th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery, Inc",

pages = "582--584",

booktitle = "RecSys 2020 - 14th ACM Conference on Recommender Systems",

}

TY - GEN

T1 - AutoRec

T2 - 14th ACM Conference on Recommender Systems, RecSys 2020

AU - Wang, Ting Hsiang

AU - Hu, Xia

AU - Jin, Haifeng

AU - Song, Qingquan

AU - Han, Xiaotian

AU - Liu, Zirui

PY - 2020/9/22

Y1 - 2020/9/22

N2 - Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec 1 2, an open-source automated machine learning (AutoML) platform extended from the TensorFlow [3] ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models. AutoRec also supports a highly flexible pipeline that accommodates both sparse and dense inputs, rating prediction and click-through rate (CTR) prediction tasks, and an array of recommendation models. Lastly, AutoRec provides a simple, user-friendly API. Experiments conducted on the benchmark datasets reveal AutoRec is reliable and can identify models which resemble the best model without prior knowledge.

AB - Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec 1 2, an open-source automated machine learning (AutoML) platform extended from the TensorFlow [3] ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models. AutoRec also supports a highly flexible pipeline that accommodates both sparse and dense inputs, rating prediction and click-through rate (CTR) prediction tasks, and an array of recommendation models. Lastly, AutoRec provides a simple, user-friendly API. Experiments conducted on the benchmark datasets reveal AutoRec is reliable and can identify models which resemble the best model without prior knowledge.

KW - Automated Machine Learning

KW - Hyperparameter Tuning

KW - Model Search

KW - Neural Architecture Search

KW - Recommender Systems

UR - http://www.scopus.com/inward/record.url?scp=85092691657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85092691657&partnerID=8YFLogxK

U2 - 10.1145/3383313.3411529

DO - 10.1145/3383313.3411529

M3 - Conference contribution

AN - SCOPUS:85092691657

T3 - RecSys 2020 - 14th ACM Conference on Recommender Systems

SP - 582

EP - 584

BT - RecSys 2020 - 14th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

Y2 - 22 September 2020 through 26 September 2020

ER -

AutoRec: An Automated Recommender System

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this