Gated attentive-autoencoder for content-aware recommendation

Chen Ma, Peng Kang, Bin Wu, Qinglong Wang, Xue Liu

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

3 Citations (Scopus)

Abstract

The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items, personalized recommender systems still face several challenging problems: (1) the hardness of exploiting sparse implicit feedback; (2) the difficulty of combining heterogeneous data. To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure. Based on the fused representations, our model exploits neighboring relations between items to help infer users' preferences. In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder. The word-level attention learns the item hidden representations from items' word sequences, while favoring informative words by assigning larger attention weights. The neighbor-level attention learns the hidden representation of an item's neighborhood by considering its neighbors in a weighted manner. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on four real-world datasets. The experimental results not only demonstrate the effectiveness of our model on top-N recommendation but also provide interpretable results attributed to the attention modules.

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
Pages519-527
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

Recommender systems
Mobile devices
Hardness
Internet
Feedback

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software
  • Computer Science Applications

Cite this

Ma, C., Kang, P., Wu, B., Wang, Q., & Liu, X. (2019). Gated attentive-autoencoder for content-aware recommendation. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining (pp. 519-527). (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining). Association for Computing Machinery, Inc. https://doi.org/10.1145/3289600.3290977
Ma, Chen ; Kang, Peng ; Wu, Bin ; Wang, Qinglong ; Liu, Xue. / Gated attentive-autoencoder for content-aware recommendation. WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. pp. 519-527 (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining).
@inproceedings{64b61b7384944d7ebe1a97fad066509f,
title = "Gated attentive-autoencoder for content-aware recommendation",
abstract = "The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items, personalized recommender systems still face several challenging problems: (1) the hardness of exploiting sparse implicit feedback; (2) the difficulty of combining heterogeneous data. To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure. Based on the fused representations, our model exploits neighboring relations between items to help infer users' preferences. In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder. The word-level attention learns the item hidden representations from items' word sequences, while favoring informative words by assigning larger attention weights. The neighbor-level attention learns the hidden representation of an item's neighborhood by considering its neighbors in a weighted manner. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on four real-world datasets. The experimental results not only demonstrate the effectiveness of our model on top-N recommendation but also provide interpretable results attributed to the attention modules.",
author = "Chen Ma and Peng Kang and Bin Wu and Qinglong Wang and Xue Liu",
year = "2019",
month = "1",
day = "30",
doi = "10.1145/3289600.3290977",
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 = "519--527",
booktitle = "WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining",

}

Ma, C, Kang, P, Wu, B, Wang, Q & Liu, X 2019, Gated attentive-autoencoder for content-aware recommendation. 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. 519-527, 12th ACM International Conference on Web Search and Data Mining, WSDM 2019, Melbourne, Australia, 2/11/19. https://doi.org/10.1145/3289600.3290977

Gated attentive-autoencoder for content-aware recommendation. / Ma, Chen; Kang, Peng; Wu, Bin; Wang, Qinglong; Liu, Xue.

WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2019. p. 519-527 (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 - Gated attentive-autoencoder for content-aware recommendation

AU - Ma, Chen

AU - Kang, Peng

AU - Wu, Bin

AU - Wang, Qinglong

AU - Liu, Xue

PY - 2019/1/30

Y1 - 2019/1/30

N2 - The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items, personalized recommender systems still face several challenging problems: (1) the hardness of exploiting sparse implicit feedback; (2) the difficulty of combining heterogeneous data. To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure. Based on the fused representations, our model exploits neighboring relations between items to help infer users' preferences. In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder. The word-level attention learns the item hidden representations from items' word sequences, while favoring informative words by assigning larger attention weights. The neighbor-level attention learns the hidden representation of an item's neighborhood by considering its neighbors in a weighted manner. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on four real-world datasets. The experimental results not only demonstrate the effectiveness of our model on top-N recommendation but also provide interpretable results attributed to the attention modules.

AB - The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. However, with the tremendous increase of users and items, personalized recommender systems still face several challenging problems: (1) the hardness of exploiting sparse implicit feedback; (2) the difficulty of combining heterogeneous data. To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating structure. Based on the fused representations, our model exploits neighboring relations between items to help infer users' preferences. In particular, a word-level and a neighbor-level attention module are integrated with the autoencoder. The word-level attention learns the item hidden representations from items' word sequences, while favoring informative words by assigning larger attention weights. The neighbor-level attention learns the hidden representation of an item's neighborhood by considering its neighbors in a weighted manner. We extensively evaluate our model with several state-of-the-art methods and different validation metrics on four real-world datasets. The experimental results not only demonstrate the effectiveness of our model on top-N recommendation but also provide interpretable results attributed to the attention modules.

UR - http://www.scopus.com/inward/record.url?scp=85061698813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061698813&partnerID=8YFLogxK

U2 - 10.1145/3289600.3290977

DO - 10.1145/3289600.3290977

M3 - Conference contribution

AN - SCOPUS:85061698813

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

SP - 519

EP - 527

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

PB - Association for Computing Machinery, Inc

ER -

Ma C, Kang P, Wu B, Wang Q, Liu X. Gated attentive-autoencoder for content-aware recommendation. In WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc. 2019. p. 519-527. (WSDM 2019 - Proceedings of the 12th ACM International Conference on Web Search and Data Mining). https://doi.org/10.1145/3289600.3290977