Hybrid Graph Neural Network Recommendation Based on Multi-Behavior Interaction and Time Sequence Awareness

Jia, Mingyu; Fang-ai, Liu; Li, Xinmeng; Zhuang, Xuqiang

doi:10.3390/electronics12051223

Cited by 5 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He et al (2022) proposed explicit semantic encoding for edges based on different user behaviors and introduced a heterogeneous graph convolutional collaborative filtering framework integrating message-passing mechanisms. Jia et al (2023) integrated user-item multibehavior interaction sequences through a joint learning mechanism and proposed the UMBGN model by using BiGRU units and AUGRU units to learn the temporally ordered user-item interaction information. The recently popular NGCF (Wang et al , 2019) model is a renowned approach for mobile application recommendations.…”

Section: Related Workmentioning

confidence: 99%

TN-MR: topic-aware neural network-based mobile application recommendation

Chen,

Cao,

Peng

et al. 2024

IJWIS

View full text Add to dashboard Cite

Purpose With the increasing number of mobile applications, efficiently recommending mobile applications to users has become a challenging problem. Although existing mobile application recommendation approaches based on user attributes and behaviors have achieved notable effectiveness, they overlook the diffusion patterns and interdependencies of topic-specific mobile applications among user groups. mobile applications among user groups. This paper aims to capture the diffusion patterns and interdependencies of mobile applications among user groups. To achieve this, a topic-aware neural network-based mobile application recommendation method, referred to as TN-MR, is proposed. Design/methodology/approach In this method, first, the user representations are enhanced by introducing a topic-aware attention layer, which captures both the topic context and the diffusion history context. Second, it exploits a time-decay mechanism to simulate changes in user interest. Multitopic user representations are aggregated by the time decay module to output the user representations of cascading representations under multiple topics. Finally, user scores that are likely to download the mobile application are predicted and ranked. Findings Experimental comparisons and analyses were conducted on the actual 360App data set, and the results demonstrate that the effectiveness of mobile application recommendations can be significantly improved by using TN-MR. Originality/value In this paper, the authors propose a mobile application recommendation method based on topic-aware attention networks. By capturing the diffusion patterns and dependencies of mobile applications, it effectively assists users in selecting their applications of interest from thousands of options, significantly improving the accuracy of mobile application recommendations.

show abstract

Section: Related Workmentioning

confidence: 99%

TN-MR: topic-aware neural network-based mobile application recommendation

Chen,

Cao,

Peng

et al. 2024

IJWIS

View full text Add to dashboard Cite

show abstract

“…Jia et al [13] proposed a new hybrid graph network recommendation model called the user multi-behavior graph network (UMBGN) to make full use of multi-behavior user-interaction information. This model used a joint learning mechanism to integrate user-item multi-behavior interaction sequences and a user multi-behavior informationaware layer was designed to focus on the long-term multi-behavior features of users and learn temporally ordered user-item interaction information through BiGRU and AUGRU units.…”

Section: Pattern Recognitionmentioning

confidence: 99%

Advanced Machine Learning Applications in Big Data Analytics

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…In a 2022 study by Yu et al [11], the graph-neural-network-based hybrid model (GNNH) leveraged graph neural networks (GNNs) to capture items and feature representations, preserving global item-item and feature-feature relationships. Mingyu et al [13] proposed a new hybrid graph network recommendation model called the user multi-behavior graph network (UMBGN), by integrating user-item multi-behavior interaction sequences, using a joint learning mechanism. This model extracts the long-term multi-behavior features of users through the user multi-behavior information perception layer, and learns the time-ordered user-item interaction information through BiGRU and AUGRU units.…”

Section: Graph Neural Networkmentioning

confidence: 99%

“…In recent years, the emergence of graph neural networks has given an excellent solution for non-Euclidean graph structure data. Graph neural networks have been widely used in recommendation systems [3][4][5][6][7][8][9][10][11][12][13], social networks [14], drug discovery [15,16], fraud detection [17,18], and other fields, because they can aggregate high-order neighbor features on graph structure data, enhance node representation, and enable it to better express node information.…”

Section: Introductionmentioning

confidence: 99%

Research on Efficient Multi-Behavior Recommendation Method Fused with Graph Neural Network

Deng

2023

Electronics

View full text Add to dashboard Cite

Currently, most recommendation algorithms only use a single type of user behavior information to predict the target behavior. However, when browsing and selecting items, users generate other types of behavior information, which is important, but often not analyzed or modeled by traditional recommendation algorithms. This study aims to design a multi-behavior recommendation algorithm based on graph neural networks by analyzing multiple types of behavior information in users’ product purchasing process, to fully utilize multiple types of user behavior information. The algorithm models users, items, and user behavior in multiple dimensions by incorporating attention mechanisms and multi-behavior learning into graph neural networks, and solves the problem of imbalanced user behavior weights from the perspective of multi-task loss optimization. After experimental verification, we proposed that the multi-behavior graph attention network (MGAT) algorithm has better performance compared to four other classical recommendation algorithms on the Beibei and Taobao datasets. The results demonstrate that the multi-behavior recommendation algorithm based on graph neural networks has practicality in fully utilizing multiple types of user information, and can solve the problem of imbalanced user behavior weights to some extent.

show abstract

Hybrid Graph Neural Network Recommendation Based on Multi-Behavior Interaction and Time Sequence Awareness

Cited by 5 publications

References 31 publications

TN-MR: topic-aware neural network-based mobile application recommendation

TN-MR: topic-aware neural network-based mobile application recommendation

Advanced Machine Learning Applications in Big Data Analytics

Research on Efficient Multi-Behavior Recommendation Method Fused with Graph Neural Network

Contact Info

Product

Resources

About