Adaptive Frequency Domain Data Augmentation for Sequential Recommendation

The sequential recommendation aims to predict users’ future interests or needs by analyzing their behavioral data over some time. Most existing approaches model user preference in the time domain, ignoring the impact of different frequency patterns (periodic features) on users’...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhibin Yang, Jiwei Qin, Donghao Zhang, Jie Ma, Peichen Ji
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10753583/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850146411146903552
author Zhibin Yang
Jiwei Qin
Donghao Zhang
Jie Ma
Peichen Ji
author_facet Zhibin Yang
Jiwei Qin
Donghao Zhang
Jie Ma
Peichen Ji
author_sort Zhibin Yang
collection DOAJ
description The sequential recommendation aims to predict users’ future interests or needs by analyzing their behavioral data over some time. Most existing approaches model user preference in the time domain, ignoring the impact of different frequency patterns (periodic features) on users’ behaviors. These frequency patterns are often intertwined in the time domain and are difficult to distinguish. However, few studies have explored how to extract frequency domain information from user behavior sequences. In addition, according to the F-principle, deep learning models pay more attention to low-frequency information, which may lead to poor performance in high-frequency tasks. To alleviate these problems, we propose a new self-supervised learning framework (AFSRec) to extract frequency features from user behavioral data. Specifically, we devise a learnable Fourier layer and a mixing for information preservation module to adaptively learn the user’s period features. In the mixed module, we utilize self-supervised signals from different frequency bands as mix samples to accommodate events of different frequency sizes while alleviating the limitation of low-frequency preference. Finally, we design a frequency domain alignment loss to align different views of the same user and jointly optimize the recommendation loss. Extensive experiments on five benchmark datasets demonstrate the superior performance of the model compared to state-of-the-art baseline methods.
format Article
id doaj-art-ec9d3dde1c5e4f8bae96e7b947e8d538
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ec9d3dde1c5e4f8bae96e7b947e8d5382025-08-20T02:27:50ZengIEEEIEEE Access2169-35362024-01-011217390217391310.1109/ACCESS.2024.349894810753583Adaptive Frequency Domain Data Augmentation for Sequential RecommendationZhibin Yang0https://orcid.org/0009-0005-8660-7333Jiwei Qin1Donghao Zhang2Jie Ma3Peichen Ji4School of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaKey Laboratory of Signal Detection and Processing, Xinjiang Uygur Autonomous Region, Xinjiang University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaSchool of Computer Science and Technology, Xinjiang University, Ürümqi, ChinaThe sequential recommendation aims to predict users’ future interests or needs by analyzing their behavioral data over some time. Most existing approaches model user preference in the time domain, ignoring the impact of different frequency patterns (periodic features) on users’ behaviors. These frequency patterns are often intertwined in the time domain and are difficult to distinguish. However, few studies have explored how to extract frequency domain information from user behavior sequences. In addition, according to the F-principle, deep learning models pay more attention to low-frequency information, which may lead to poor performance in high-frequency tasks. To alleviate these problems, we propose a new self-supervised learning framework (AFSRec) to extract frequency features from user behavioral data. Specifically, we devise a learnable Fourier layer and a mixing for information preservation module to adaptively learn the user’s period features. In the mixed module, we utilize self-supervised signals from different frequency bands as mix samples to accommodate events of different frequency sizes while alleviating the limitation of low-frequency preference. Finally, we design a frequency domain alignment loss to align different views of the same user and jointly optimize the recommendation loss. Extensive experiments on five benchmark datasets demonstrate the superior performance of the model compared to state-of-the-art baseline methods.https://ieeexplore.ieee.org/document/10753583/Sequential recommendationadaptivefrequency domaindata augmentation
spellingShingle Zhibin Yang
Jiwei Qin
Donghao Zhang
Jie Ma
Peichen Ji
Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
IEEE Access
Sequential recommendation
adaptive
frequency domain
data augmentation
title Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
title_full Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
title_fullStr Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
title_full_unstemmed Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
title_short Adaptive Frequency Domain Data Augmentation for Sequential Recommendation
title_sort adaptive frequency domain data augmentation for sequential recommendation
topic Sequential recommendation
adaptive
frequency domain
data augmentation
url https://ieeexplore.ieee.org/document/10753583/
work_keys_str_mv AT zhibinyang adaptivefrequencydomaindataaugmentationforsequentialrecommendation
AT jiweiqin adaptivefrequencydomaindataaugmentationforsequentialrecommendation
AT donghaozhang adaptivefrequencydomaindataaugmentationforsequentialrecommendation
AT jiema adaptivefrequencydomaindataaugmentationforsequentialrecommendation
AT peichenji adaptivefrequencydomaindataaugmentationforsequentialrecommendation