FuzzAttention on Session-based Recommender System

Chi Shiang Wang, Jung Hsien Chiang

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

Abstract

mender system is studied widely and has been implemented successfully into businesses and daily lives. Its primary purpose is to analyze user behaviors to predict the next item of interest. To enrich user information, a session-based recommender system considers the user's historical records in the session. This information includes the user's general and current interests as additional information to improve the performance of the model such that the next item can be recommended easily. However, the recommender system not only considers the prediction performance but also regards the interpretability as a major target. For enhancing the interpretability and performance, we propose a novel mechanism, i.e., FuzzAttention, based on the attention mechanism that is applied widely to deep-learning models. In FuzzAttention, we utilize a fuzzy neural network to build a fuzzy inference system; therefore, we adopt joint learning to learn the parameters in the session-based recommendation and the fuzzy neural network jointly. In the experiments, we used two types of session-based recommender systems and conducted them on two datasets including the session-based information to compare the model performance based on the traditional attention mechanism and FuzzAttention. The results indicate that our proposed mechanism can improve the performance to predict the next item and the model's interpretability.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538617281
DOIs
Publication statusPublished - 2019 Jun
Event2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019 - New Orleans, United States
Duration: 2019 Jun 232019 Jun 26

Publication series

NameIEEE International Conference on Fuzzy Systems
Volume2019-June
ISSN (Print)1098-7584

Conference

Conference2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019
CountryUnited States
CityNew Orleans
Period19-06-2319-06-26

Fingerprint

Recommender Systems
Recommender systems
Interpretability
Fuzzy neural networks
Fuzzy Neural Network
Predict
Fuzzy Inference System
User Behavior
Performance Prediction
Fuzzy inference
Performance Model
Recommendations
Model
Target
Experiment
Industry
Experiments
Learning

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Wang, C. S., & Chiang, J. H. (2019). FuzzAttention on Session-based Recommender System. In 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019 [8858856] (IEEE International Conference on Fuzzy Systems; Vol. 2019-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FUZZ-IEEE.2019.8858856
Wang, Chi Shiang ; Chiang, Jung Hsien. / FuzzAttention on Session-based Recommender System. 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (IEEE International Conference on Fuzzy Systems).
@inproceedings{a2e3bf0784a04971afa3a26f8bfb7b6e,
title = "FuzzAttention on Session-based Recommender System",
abstract = "mender system is studied widely and has been implemented successfully into businesses and daily lives. Its primary purpose is to analyze user behaviors to predict the next item of interest. To enrich user information, a session-based recommender system considers the user's historical records in the session. This information includes the user's general and current interests as additional information to improve the performance of the model such that the next item can be recommended easily. However, the recommender system not only considers the prediction performance but also regards the interpretability as a major target. For enhancing the interpretability and performance, we propose a novel mechanism, i.e., FuzzAttention, based on the attention mechanism that is applied widely to deep-learning models. In FuzzAttention, we utilize a fuzzy neural network to build a fuzzy inference system; therefore, we adopt joint learning to learn the parameters in the session-based recommendation and the fuzzy neural network jointly. In the experiments, we used two types of session-based recommender systems and conducted them on two datasets including the session-based information to compare the model performance based on the traditional attention mechanism and FuzzAttention. The results indicate that our proposed mechanism can improve the performance to predict the next item and the model's interpretability.",
author = "Wang, {Chi Shiang} and Chiang, {Jung Hsien}",
year = "2019",
month = "6",
doi = "10.1109/FUZZ-IEEE.2019.8858856",
language = "English",
series = "IEEE International Conference on Fuzzy Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019",
address = "United States",

}

Wang, CS & Chiang, JH 2019, FuzzAttention on Session-based Recommender System. in 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019., 8858856, IEEE International Conference on Fuzzy Systems, vol. 2019-June, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019, New Orleans, United States, 19-06-23. https://doi.org/10.1109/FUZZ-IEEE.2019.8858856

FuzzAttention on Session-based Recommender System. / Wang, Chi Shiang; Chiang, Jung Hsien.

2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8858856 (IEEE International Conference on Fuzzy Systems; Vol. 2019-June).

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

TY - GEN

T1 - FuzzAttention on Session-based Recommender System

AU - Wang, Chi Shiang

AU - Chiang, Jung Hsien

PY - 2019/6

Y1 - 2019/6

N2 - mender system is studied widely and has been implemented successfully into businesses and daily lives. Its primary purpose is to analyze user behaviors to predict the next item of interest. To enrich user information, a session-based recommender system considers the user's historical records in the session. This information includes the user's general and current interests as additional information to improve the performance of the model such that the next item can be recommended easily. However, the recommender system not only considers the prediction performance but also regards the interpretability as a major target. For enhancing the interpretability and performance, we propose a novel mechanism, i.e., FuzzAttention, based on the attention mechanism that is applied widely to deep-learning models. In FuzzAttention, we utilize a fuzzy neural network to build a fuzzy inference system; therefore, we adopt joint learning to learn the parameters in the session-based recommendation and the fuzzy neural network jointly. In the experiments, we used two types of session-based recommender systems and conducted them on two datasets including the session-based information to compare the model performance based on the traditional attention mechanism and FuzzAttention. The results indicate that our proposed mechanism can improve the performance to predict the next item and the model's interpretability.

AB - mender system is studied widely and has been implemented successfully into businesses and daily lives. Its primary purpose is to analyze user behaviors to predict the next item of interest. To enrich user information, a session-based recommender system considers the user's historical records in the session. This information includes the user's general and current interests as additional information to improve the performance of the model such that the next item can be recommended easily. However, the recommender system not only considers the prediction performance but also regards the interpretability as a major target. For enhancing the interpretability and performance, we propose a novel mechanism, i.e., FuzzAttention, based on the attention mechanism that is applied widely to deep-learning models. In FuzzAttention, we utilize a fuzzy neural network to build a fuzzy inference system; therefore, we adopt joint learning to learn the parameters in the session-based recommendation and the fuzzy neural network jointly. In the experiments, we used two types of session-based recommender systems and conducted them on two datasets including the session-based information to compare the model performance based on the traditional attention mechanism and FuzzAttention. The results indicate that our proposed mechanism can improve the performance to predict the next item and the model's interpretability.

UR - http://www.scopus.com/inward/record.url?scp=85073807624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073807624&partnerID=8YFLogxK

U2 - 10.1109/FUZZ-IEEE.2019.8858856

DO - 10.1109/FUZZ-IEEE.2019.8858856

M3 - Conference contribution

AN - SCOPUS:85073807624

T3 - IEEE International Conference on Fuzzy Systems

BT - 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wang CS, Chiang JH. FuzzAttention on Session-based Recommender System. In 2019 IEEE International Conference on Fuzzy Systems, FUZZ 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8858856. (IEEE International Conference on Fuzzy Systems). https://doi.org/10.1109/FUZZ-IEEE.2019.8858856