Local Collaborative Autoencoders

Minjin Choi; Yoonki Jeong; Joonseok Lee; Jongwuk Lee

doi:10.1145/3437963.3441808

Local Collaborative Autoencoders

Minjin Choi
, Yoonki Jeong
, Joonseok Lee
, Jongwuk Lee

Department of Computer Science and Engineering

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

21 Scopus citations

Abstract

This work presents a generalized local factor model, namely Local Collaborative Autoencoders (LOCA). To our knowledge, it is the first generalized framework under the local low-rank assumption that builds on the neural recommendation models. We explore a large number of local models by adopting a generalized framework with different weight schemes for training and aggregating them. Besides, we develop a novel method of discovering a sub-community to maximize the coverage of local models. Our experimental results demonstrate that LOCA is highly scalable, achieving state-of-the-art results by outperforming existing AE-based and local latent factor models on several large-scale public benchmarks.

Original language	English
Title of host publication	WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining
Publisher	Association for Computing Machinery, Inc
Pages	734-742
Number of pages	9
ISBN (Electronic)	9781450382977
DOIs	https://doi.org/10.1145/3437963.3441808
State	Published - 3 Aug 2021
Event	14th ACM International Conference on Web Search and Data Mining, WSDM 2021 - Virtual, Online, Israel Duration: 8 Mar 2021 → 12 Mar 2021

Publication series

Name	WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining

Conference

Conference	14th ACM International Conference on Web Search and Data Mining, WSDM 2021
Country/Territory	Israel
City	Virtual, Online
Period	8/03/21 → 12/03/21

Keywords

autoencoders
collaborative filtering
local latent factor model

Access to Document

10.1145/3437963.3441808

Cite this

Choi, M., Jeong, Y., Lee, J., & Lee, J. (2021). Local Collaborative Autoencoders. In WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining (pp. 734-742). (WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining). Association for Computing Machinery, Inc. https://doi.org/10.1145/3437963.3441808

@inproceedings{e699f7b94e204a498b22d2e3541268c6,

title = "Local Collaborative Autoencoders",

abstract = "This work presents a generalized local factor model, namely Local Collaborative Autoencoders (LOCA). To our knowledge, it is the first generalized framework under the local low-rank assumption that builds on the neural recommendation models. We explore a large number of local models by adopting a generalized framework with different weight schemes for training and aggregating them. Besides, we develop a novel method of discovering a sub-community to maximize the coverage of local models. Our experimental results demonstrate that LOCA is highly scalable, achieving state-of-the-art results by outperforming existing AE-based and local latent factor models on several large-scale public benchmarks.",

keywords = "autoencoders, collaborative filtering, local latent factor model",

author = "Minjin Choi and Yoonki Jeong and Joonseok Lee and Jongwuk Lee",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 14th ACM International Conference on Web Search and Data Mining, WSDM 2021 ; Conference date: 08-03-2021 Through 12-03-2021",

year = "2021",

month = aug,

day = "3",

doi = "10.1145/3437963.3441808",

language = "English",

series = "WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining",

publisher = "Association for Computing Machinery, Inc",

pages = "734--742",

booktitle = "WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining",

}

Choi, M, Jeong, Y, Lee, J & Lee, J 2021, Local Collaborative Autoencoders. in WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining. WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, Inc, pp. 734-742, 14th ACM International Conference on Web Search and Data Mining, WSDM 2021, Virtual, Online, Israel, 8/03/21. https://doi.org/10.1145/3437963.3441808

Local Collaborative Autoencoders. / Choi, Minjin; Jeong, Yoonki; Lee, Joonseok et al.
WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2021. p. 734-742 (WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining).

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

TY - GEN

T1 - Local Collaborative Autoencoders

AU - Choi, Minjin

AU - Jeong, Yoonki

AU - Lee, Joonseok

AU - Lee, Jongwuk

PY - 2021/8/3

Y1 - 2021/8/3

N2 - This work presents a generalized local factor model, namely Local Collaborative Autoencoders (LOCA). To our knowledge, it is the first generalized framework under the local low-rank assumption that builds on the neural recommendation models. We explore a large number of local models by adopting a generalized framework with different weight schemes for training and aggregating them. Besides, we develop a novel method of discovering a sub-community to maximize the coverage of local models. Our experimental results demonstrate that LOCA is highly scalable, achieving state-of-the-art results by outperforming existing AE-based and local latent factor models on several large-scale public benchmarks.

AB - This work presents a generalized local factor model, namely Local Collaborative Autoencoders (LOCA). To our knowledge, it is the first generalized framework under the local low-rank assumption that builds on the neural recommendation models. We explore a large number of local models by adopting a generalized framework with different weight schemes for training and aggregating them. Besides, we develop a novel method of discovering a sub-community to maximize the coverage of local models. Our experimental results demonstrate that LOCA is highly scalable, achieving state-of-the-art results by outperforming existing AE-based and local latent factor models on several large-scale public benchmarks.

KW - autoencoders

KW - collaborative filtering

KW - local latent factor model

UR - https://www.scopus.com/pages/publications/85103040099

U2 - 10.1145/3437963.3441808

DO - 10.1145/3437963.3441808

M3 - Conference contribution

AN - SCOPUS:85103040099

T3 - WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining

SP - 734

EP - 742

BT - WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery, Inc

T2 - 14th ACM International Conference on Web Search and Data Mining, WSDM 2021

Y2 - 8 March 2021 through 12 March 2021

ER -

Local Collaborative Autoencoders

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this