Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation

Existing multi-behavior sequential recommendation methods obtain users’ interest preferences by analyzing their historical multi-behavior information to uncover users’ potential intentions in multi-behavior sequential recommendation. However, the existing methods still have pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Sitong Yan, Chao Zhao, Ningning Shen, Shaopeng Jiang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10786978/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850251019011751936
author Sitong Yan
Chao Zhao
Ningning Shen
Shaopeng Jiang
author_facet Sitong Yan
Chao Zhao
Ningning Shen
Shaopeng Jiang
author_sort Sitong Yan
collection DOAJ
description Existing multi-behavior sequential recommendation methods obtain users’ interest preferences by analyzing their historical multi-behavior information to uncover users’ potential intentions in multi-behavior sequential recommendation. However, the existing methods still have problems such as unstable users’ interest preferences and difficulty in capturing the fine-grained relationships between behaviors. This paper proposes a framework called Position-aware Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation (PHCL-MBSR). It introduces position context encoding in the temporal dimension, focusing on the context behavior dependencies. In the spatial dimension, a global hypergraph is constructed to capture the high-order relationships between sequences, and the global multi-behavior dependencies in the spatial dimension are captured through hypergraph contrastive learning. PHCL-MBSR has been experimentally evaluated on three benchmark datasets, and the results demonstrate the effectiveness and interpretability of this framework.
format Article
id doaj-art-3db3035b118f4902a171038ee07d3d40
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3db3035b118f4902a171038ee07d3d402025-08-20T01:58:00ZengIEEEIEEE Access2169-35362024-01-011218595818597010.1109/ACCESS.2024.351398210786978Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence RecommendationSitong Yan0https://orcid.org/0009-0007-8461-5334Chao Zhao1https://orcid.org/0000-0002-0736-7898Ningning Shen2Shaopeng Jiang3https://orcid.org/0009-0009-1508-0422School of Information and Electrical Engineering, Hebei University of Engineering, Handan, ChinaSchool of Information and Electrical Engineering, Hebei University of Engineering, Handan, ChinaSchool of Information and Electrical Engineering, Hebei University of Engineering, Handan, ChinaSchool of Information and Electrical Engineering, Hebei University of Engineering, Handan, ChinaExisting multi-behavior sequential recommendation methods obtain users’ interest preferences by analyzing their historical multi-behavior information to uncover users’ potential intentions in multi-behavior sequential recommendation. However, the existing methods still have problems such as unstable users’ interest preferences and difficulty in capturing the fine-grained relationships between behaviors. This paper proposes a framework called Position-aware Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation (PHCL-MBSR). It introduces position context encoding in the temporal dimension, focusing on the context behavior dependencies. In the spatial dimension, a global hypergraph is constructed to capture the high-order relationships between sequences, and the global multi-behavior dependencies in the spatial dimension are captured through hypergraph contrastive learning. PHCL-MBSR has been experimentally evaluated on three benchmark datasets, and the results demonstrate the effectiveness and interpretability of this framework.https://ieeexplore.ieee.org/document/10786978/Hypergraph neural networksequential recommendationmulti-behavior recommendationcontrastive learning
spellingShingle Sitong Yan
Chao Zhao
Ningning Shen
Shaopeng Jiang
Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
IEEE Access
Hypergraph neural network
sequential recommendation
multi-behavior recommendation
contrastive learning
title Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
title_full Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
title_fullStr Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
title_full_unstemmed Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
title_short Position-Awareness and Hypergraph Contrastive Learning for Multi-Behavior Sequence Recommendation
title_sort position awareness and hypergraph contrastive learning for multi behavior sequence recommendation
topic Hypergraph neural network
sequential recommendation
multi-behavior recommendation
contrastive learning
url https://ieeexplore.ieee.org/document/10786978/
work_keys_str_mv AT sitongyan positionawarenessandhypergraphcontrastivelearningformultibehaviorsequencerecommendation
AT chaozhao positionawarenessandhypergraphcontrastivelearningformultibehaviorsequencerecommendation
AT ningningshen positionawarenessandhypergraphcontrastivelearningformultibehaviorsequencerecommendation
AT shaopengjiang positionawarenessandhypergraphcontrastivelearningformultibehaviorsequencerecommendation