AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation

Traditional systems often focus on a singular action type, such as a purchase, while overlooking the rich behavioral pluralism that is inherent in user engagement, such as the transient clicks or latent purchase intents signaled by cart additions. This narrow focus leads to sparse datasets and hinde...

Full description

Saved in:
Bibliographic Details
Main Authors: Ritchie Natuan Caibigan, Punyaphol Horata, Pusadee Seresangtakul
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11052242/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428605971464192
author Ritchie Natuan Caibigan
Punyaphol Horata
Pusadee Seresangtakul
author_facet Ritchie Natuan Caibigan
Punyaphol Horata
Pusadee Seresangtakul
author_sort Ritchie Natuan Caibigan
collection DOAJ
description Traditional systems often focus on a singular action type, such as a purchase, while overlooking the rich behavioral pluralism that is inherent in user engagement, such as the transient clicks or latent purchase intents signaled by cart additions. This narrow focus leads to sparse datasets and hinders recommendation accuracy. In response to the evolving landscape of real-time recommendation systems, contemporary frameworks are increasingly leveraging dynamic user engagement streams that span actions, such as purchasing, item retention, and exploratory browsing, to refine suggestions. To bridge this gap, we introduce a novel and revolutionary model: adaptive ensemble graph neural networks (GNNs), for multibehavior stream recommendation (AEMS). The AEMS synergizes long-term preference patterns (derived from historical interactions) with real-time user intents and item attributes (captured through multibehavior signals), integrating them via an adaptive ensemble neural gating mechanism. This design effectively fuses multifaceted behaviors and addresses the challenges of data sparsity and heterogeneity. This architecture is further enhanced by a behavior-aware training paradigm that dynamically weights heterogeneous interactions, such as clicks, add-to-cart actions, likes, and other behavioral signals, to increase its recommendation precision. Extensive experiments conducted on real-world datasets demonstrate that the AEMS significantly outperforms the state-of-the-art methods, demonstrating its ability to decode complex, high-order synergies in streaming environments.
format Article
id doaj-art-9a65df8a0f8944eca195dd6e2004acc6
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-9a65df8a0f8944eca195dd6e2004acc62025-08-20T03:28:38ZengIEEEIEEE Access2169-35362025-01-011311469611471510.1109/ACCESS.2025.358342511052242AEMS: Adaptive Ensemble GNNs for Multibehavior Stream RecommendationRitchie Natuan Caibigan0https://orcid.org/0009-0007-5626-2340Punyaphol Horata1https://orcid.org/0000-0001-9245-7400Pusadee Seresangtakul2https://orcid.org/0000-0001-7579-2485College of Computing, Khon Kaen University, Khon Kaen, ThailandCollege of Computing, Khon Kaen University, Khon Kaen, ThailandCollege of Computing, Khon Kaen University, Khon Kaen, ThailandTraditional systems often focus on a singular action type, such as a purchase, while overlooking the rich behavioral pluralism that is inherent in user engagement, such as the transient clicks or latent purchase intents signaled by cart additions. This narrow focus leads to sparse datasets and hinders recommendation accuracy. In response to the evolving landscape of real-time recommendation systems, contemporary frameworks are increasingly leveraging dynamic user engagement streams that span actions, such as purchasing, item retention, and exploratory browsing, to refine suggestions. To bridge this gap, we introduce a novel and revolutionary model: adaptive ensemble graph neural networks (GNNs), for multibehavior stream recommendation (AEMS). The AEMS synergizes long-term preference patterns (derived from historical interactions) with real-time user intents and item attributes (captured through multibehavior signals), integrating them via an adaptive ensemble neural gating mechanism. This design effectively fuses multifaceted behaviors and addresses the challenges of data sparsity and heterogeneity. This architecture is further enhanced by a behavior-aware training paradigm that dynamically weights heterogeneous interactions, such as clicks, add-to-cart actions, likes, and other behavioral signals, to increase its recommendation precision. Extensive experiments conducted on real-world datasets demonstrate that the AEMS significantly outperforms the state-of-the-art methods, demonstrating its ability to decode complex, high-order synergies in streaming environments.https://ieeexplore.ieee.org/document/11052242/Ensemble learninggraph neural networks (GNNs)multibehavior recommendationstream recommendationrecommendation systems
spellingShingle Ritchie Natuan Caibigan
Punyaphol Horata
Pusadee Seresangtakul
AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
IEEE Access
Ensemble learning
graph neural networks (GNNs)
multibehavior recommendation
stream recommendation
recommendation systems
title AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
title_full AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
title_fullStr AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
title_full_unstemmed AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
title_short AEMS: Adaptive Ensemble GNNs for Multibehavior Stream Recommendation
title_sort aems adaptive ensemble gnns for multibehavior stream recommendation
topic Ensemble learning
graph neural networks (GNNs)
multibehavior recommendation
stream recommendation
recommendation systems
url https://ieeexplore.ieee.org/document/11052242/
work_keys_str_mv AT ritchienatuancaibigan aemsadaptiveensemblegnnsformultibehaviorstreamrecommendation
AT punyapholhorata aemsadaptiveensemblegnnsformultibehaviorstreamrecommendation
AT pusadeeseresangtakul aemsadaptiveensemblegnnsformultibehaviorstreamrecommendation