EASRec: External Attentive Efficient Sequential Recommender

Sequential recommendation task aims at modeling users’ preference according to the sequential dependencies contained in their historical interacted item sequences. The advanced self-attention mechanism, reallocating the input sequence features, reducing the inductive bias, and refining th...

Full description

Saved in:
Bibliographic Details
Main Authors: Wu Qiao, Xingliang Zhang, Chao Wu, Bing Jia, Funing Yang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10155488/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846129661638082560
author Wu Qiao
Xingliang Zhang
Chao Wu
Bing Jia
Funing Yang
author_facet Wu Qiao
Xingliang Zhang
Chao Wu
Bing Jia
Funing Yang
author_sort Wu Qiao
collection DOAJ
description Sequential recommendation task aims at modeling users’ preference according to the sequential dependencies contained in their historical interacted item sequences. The advanced self-attention mechanism, reallocating the input sequence features, reducing the inductive bias, and refining the output representations, tends to become the go-to underlying method for this task. However, since the computational complexity is quadratic correlated with the sequence length, self-attention-based sequential recommenders might be inflexible to deal with long sequences. We propose an efficient sequential recommender EASRec based on the multi-head external attention mechanism to avoid such issue. Specifically, EASRec mines the sequential dependency via two learnable memories coupled with a double normalization strategy, reducing the computational complexity from quadratic to linear. Take a step further, since the memories are global sharing, our EASRec can implicitly model the potential correlations among all sequences, i.e., the common preference, which is lack in the self-attention mechanism. We conduct numerous experiments on three public datasets, and the experimental results show that our EASRec can provide 3.63% improvement on average compared to several state-of-the-art baselines with minimal computational cost.
format Article
id doaj-art-1a8f339524f64981bf480691bc3eb547
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1a8f339524f64981bf480691bc3eb5472024-12-10T00:01:33ZengIEEEIEEE Access2169-35362024-01-011218073818074610.1109/ACCESS.2023.328764010155488EASRec: External Attentive Efficient Sequential RecommenderWu Qiao0Xingliang Zhang1Chao Wu2Bing Jia3https://orcid.org/0000-0003-3294-6303Funing Yang4College of Artificial Intelligence Industry, Changchun University of Architecture and Civil Engineering, Changchun, Jilin, ChinaChina Mobile Group Jilin Company Ltd., Changchun, Jilin, ChinaChina Mobile Communications Group Company Ltd., Beijing, ChinaCollege of Computer Science, Inner Mongolia University, Hohhot, ChinaCollege of Computer Science and Technology, Jilin University, Changchun, Jilin, ChinaSequential recommendation task aims at modeling users’ preference according to the sequential dependencies contained in their historical interacted item sequences. The advanced self-attention mechanism, reallocating the input sequence features, reducing the inductive bias, and refining the output representations, tends to become the go-to underlying method for this task. However, since the computational complexity is quadratic correlated with the sequence length, self-attention-based sequential recommenders might be inflexible to deal with long sequences. We propose an efficient sequential recommender EASRec based on the multi-head external attention mechanism to avoid such issue. Specifically, EASRec mines the sequential dependency via two learnable memories coupled with a double normalization strategy, reducing the computational complexity from quadratic to linear. Take a step further, since the memories are global sharing, our EASRec can implicitly model the potential correlations among all sequences, i.e., the common preference, which is lack in the self-attention mechanism. We conduct numerous experiments on three public datasets, and the experimental results show that our EASRec can provide 3.63% improvement on average compared to several state-of-the-art baselines with minimal computational cost.https://ieeexplore.ieee.org/document/10155488/Sequential recommendationattention mechanismdeep learning
spellingShingle Wu Qiao
Xingliang Zhang
Chao Wu
Bing Jia
Funing Yang
EASRec: External Attentive Efficient Sequential Recommender
IEEE Access
Sequential recommendation
attention mechanism
deep learning
title EASRec: External Attentive Efficient Sequential Recommender
title_full EASRec: External Attentive Efficient Sequential Recommender
title_fullStr EASRec: External Attentive Efficient Sequential Recommender
title_full_unstemmed EASRec: External Attentive Efficient Sequential Recommender
title_short EASRec: External Attentive Efficient Sequential Recommender
title_sort easrec external attentive efficient sequential recommender
topic Sequential recommendation
attention mechanism
deep learning
url https://ieeexplore.ieee.org/document/10155488/
work_keys_str_mv AT wuqiao easrecexternalattentiveefficientsequentialrecommender
AT xingliangzhang easrecexternalattentiveefficientsequentialrecommender
AT chaowu easrecexternalattentiveefficientsequentialrecommender
AT bingjia easrecexternalattentiveefficientsequentialrecommender
AT funingyang easrecexternalattentiveefficientsequentialrecommender