Linked variational autoencoders for inferring substitutable and supplementary items

Vineeth Rakesh, Suhang Wang, Kai Shu, Huan Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.

Original languageEnglish (US)
Title of host publicationWSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages438-446
Number of pages9
ISBN (Electronic)9781450359405
DOIs
StatePublished - Jan 30 2019
Event12th ACM International Conference on Web Search and Data Mining, WSDM 2019 - Melbourne, Australia
Duration: Feb 11 2019Feb 15 2019

Publication series

NameWSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining

Conference

Conference12th ACM International Conference on Web Search and Data Mining, WSDM 2019
CountryAustralia
CityMelbourne
Period2/11/192/15/19

Fingerprint

Collaborative filtering
Neural networks
Controllers
Experiments
Deep learning

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software
  • Computer Science Applications

Cite this

Rakesh, V., Wang, S., Shu, K., & Liu, H. (2019). Linked variational autoencoders for inferring substitutable and supplementary items. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining (pp. 438-446). (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining). Association for Computing Machinery, Inc. https://doi.org/10.1145/3289600.3290963
Rakesh, Vineeth ; Wang, Suhang ; Shu, Kai ; Liu, Huan. / Linked variational autoencoders for inferring substitutable and supplementary items. WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. pp. 438-446 (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining).
@inproceedings{c18e45c505d74d3cb7bdc34a51958472,
title = "Linked variational autoencoders for inferring substitutable and supplementary items",
abstract = "Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.",
author = "Vineeth Rakesh and Suhang Wang and Kai Shu and Huan Liu",
year = "2019",
month = "1",
day = "30",
doi = "10.1145/3289600.3290963",
language = "English (US)",
series = "WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining",
publisher = "Association for Computing Machinery, Inc",
pages = "438--446",
booktitle = "WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining",

}

Rakesh, V, Wang, S, Shu, K & Liu, H 2019, Linked variational autoencoders for inferring substitutable and supplementary items. in WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, Inc, pp. 438-446, 12th ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, Australia, 2/11/19. https://doi.org/10.1145/3289600.3290963

Linked variational autoencoders for inferring substitutable and supplementary items. / Rakesh, Vineeth; Wang, Suhang; Shu, Kai; Liu, Huan.

WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. p. 438-446 (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Linked variational autoencoders for inferring substitutable and supplementary items

AU - Rakesh, Vineeth

AU - Wang, Suhang

AU - Shu, Kai

AU - Liu, Huan

PY - 2019/1/30

Y1 - 2019/1/30

N2 - Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.

AB - Recommendation in the modern world is not only about capturing the interaction between users and items, but also about understanding the relationship between items. Besides improving the quality of recommendation, it enables the generation of candidate items that can serve as substitutes and supplements of another item. For example, when recommending Xbox, PS4 could be a logical substitute and the supplements could be items such as game controllers, surround system, and travel case. Therefore, given a network of items, our objective is to learn their content features such that they explain the relationship between items in terms of substitutes and supplements. To achieve this, we propose a generative deep learning model that links two variational autoencoders using a connector neural network to create Linked Variational Autoencoder (LVA). LVA learns the latent features of items by conditioning on the observed relationship between items. Using a rigorous series of experiments, we show that LVA significantly outperforms other representative and state-of-the-art baseline methods in terms of prediction accuracy. We then extend LVA by incorporating collaborative filtering (CF) to create CLVA that captures the implicit relationship between users and items. By comparing CLVA with LVA we show that inducing CF-based features greatly improve the recommendation quality of substitutable and supplementary items on a user level.

UR - http://www.scopus.com/inward/record.url?scp=85061726880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061726880&partnerID=8YFLogxK

U2 - 10.1145/3289600.3290963

DO - 10.1145/3289600.3290963

M3 - Conference contribution

T3 - WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining

SP - 438

EP - 446

BT - WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery, Inc

ER -

Rakesh V, Wang S, Shu K, Liu H. Linked variational autoencoders for inferring substitutable and supplementary items. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc. 2019. p. 438-446. (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining). https://doi.org/10.1145/3289600.3290963