Time-sequential variational conditional auto-encoders for recommendation

被引：0

作者：

Hozumi J. ^{[1
]}

Iwasawa Y. ^{[1
]}

Matsuo Y. ^{[1
]}

机构：

[1] Hozumi, Jun

[2] Iwasawa, Yusuke

[3] Matsuo, Yutaka

来源：

| 1600年 / Japanese Society for Artificial Intelligence卷 / 36期

关键词：

Deep learning; Recommendation system; Time information; Variational auto-encoder;

D O I：

10.1527/tjsai.36-3_C-KB7

中图分类号：

学科分类号：

摘要：

In this study, we propose a method for adding time of action information to a Variational Auto-encoder (VAE)based recommendation system. Since time of action is an important information to improve the accuracy of recommendation, many methods have been proposed to use the information of time of action, such as purchase or review of a product, for recommendation. And VAE-based recommendation systems have been reported to be more accurate and robust for small data sets compared to traditional deep learning-based recommendation systems. Existing research on introducing time information into VAEs includes a method of weaving information on the order in which products are preferred by passing the encoding layer consisting of RNN, but the time information of the product preferred is not considered. If the absolute time information is not taken into account when recommending a product, for example, when a temporary boom causes many users to prefer a particular product, it may be judged to be a preference based on the user’s preferences, which may adversely affect the recommendation results. Based on the above problems, this study examines a VAE-based recommendation system to improve the recommendation accuracy by adding time information of each action to the input information, and finally proposes Time-Sequential VAE (TSVAE) and confirms its accuracy. In addition, to verify how to add time information to improve the accuracy, we conducted experiments using multiple models with and without absolute time information and different encoders of time interval information, and evaluated the accuracy. © 2021, Japanese Society for Artificial Intelligence. All rights reserved.

引用

共 17 条

[1]

Adomavicius G., Tuzhilin A., Context-aware recommender systems, Recommender Systems Handbook, (2011)

[2]

Beutel A., Et al., Latent cross: Making use of context in recurrent recommender systems, Proceedings of the 11th ACM International Conference on Web Search and Data Mining, pp. 46-54, (2018)

[3]

Cheng H.-T., Et al., Wide & deep learning for recommender systems, Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7-10, (2016)

[4]

He X., Et al., Neural collaborative filtering, Proceedings of the 26th International Conference on World Wide Web, pp. 173-182, (2017)

[5]

McAuley J. J., Leskovec J., From amateurs to connoisseurs: Modeling the evolution of user expertise through online reviews, Proceedings of the 22nd International Conference on World Wide Web, pp. 897-908, (2013)

[6]

Kang W.-C., Et al., Visually-aware fashion recommendation and design with generative image models, Proceedings of 2017 IEEE International Conference on Data Mining, pp. 207-216, (2017)

[7]

Kingma D. P., Welling M., Auto-encoding variational bayes, Proceedings of 2nd International Conference on Learning Representations, (2014)

[8]

Liang D., Et al., Variational autoencoders for collaborative filtering, Proceedings of the 2018 World Wide Web Conference, pp. 689-698, (2018)

[9]

Liu H., Et al., Joint representation learning for multi-modal transportation recommendation, Proceedings of the AAAI Conference on Artificial Intelligence, 33, pp. 1036-1043, (2019)

[10]

Pavlovski M., Et al., Time-aware user embeddings as a service, Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3194-3202, (2020)

← 1 2 →