Multi-Behavior Graph Neural Networks for Recommender System

Xia, Lianghao; Huang, Chao; Xu, Yong; Dai, Pengcheng; Bo, Liefeng

doi:10.1109/tnnls.2022.3204775

Cited by 15 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the multi-behavior bipartite graphs constructed here are different from those described in previous works [14,16,19,20,36,40], as our weighted graphs actually contain explicit information on behavior interactions that was learned via the explicit behavior interaction extraction module and can more accurately reflect the user's preferences in regard to different behaviors.…”

Section: Explicit Behavior Interaction Fusion Modulementioning

confidence: 98%

Explicit Behavior Interaction with Heterogeneous Graph for Multi-behavior Recommendation

Zhang,

Jia,

Hou

et al. 2024

Data Sci. Eng.

View full text Add to dashboard Cite

Multi-behavior recommendation systems exploit multi-type user–item interactions (e.g., clicking, adding to cart and collecting) as auxiliary behaviors for user modeling, which can alleviate the problem of data sparsity faced by traditional recommendation systems. The key point of multi-behavior recommendation systems is to make full use of the auxiliary behavior information for the learning of user preferences. However, there are two challenges in existing methods that need to be explored: (1) capturing personalized user preferences based on multiple auxiliary behaviors, especially for negative feedback signals; and (2) explicitly modeling the semantics between auxiliary and target behaviors, and learning the explicit interactions between multiple behaviors. To tackle the two problems described above, we propose a novel model, called explicit behavior interaction with heterogeneous graph for multi-behavior recommendation (MB-EBIH). In particular, we first construct a heterogeneous behavior graph, including both positive and negative behaviors. A pre-trained model based on graph neural network (GNN) is then used to generate explicit behavior interaction values as the edge weights for the heterogeneous behavior graph. These weights reflect the importance of each of the auxiliary behaviors in an explicit manner. Finally, the extracted explicit behavior interaction information is incorporated into the multi-behavior user–item bipartite graphs to learn better representations. Experimental results on four real-world datasets demonstrate the effectiveness of our model in terms of exploring multi-behavioral data; and ablation and analysis experiments further demonstrate the effectiveness of explicit behavior interaction information.

show abstract

Section: Explicit Behavior Interaction Fusion Modulementioning

confidence: 98%

Explicit Behavior Interaction with Heterogeneous Graph for Multi-behavior Recommendation

Zhang,

Jia,

Hou

et al. 2024

Data Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Understanding user behavior and preferences is pivotal. User interactions like item views, clicks, purchases, and ratings provide rich insights, particularly in session-based recommendations [190], [191]. User profiling, aided by techniques like graph neural networks [192] and social graph neural networks [193], captures preferences.…”

Section: E: User Behavior and Preferences For Personalizationmentioning

confidence: 99%

“…User behavior refers to the actions and interactions of users within the recommendation system, such as the items they view, click, purchase, or rate. These behaviors are commonly used in session-based recommendations [87], [190], [195], [196], and can provide rich information for understanding user preferences [191].…”

Section: E: User Behavior and Preferences For Personalizationmentioning

confidence: 99%

Deep Learning-Based Recommendation System: Systematic Review and Classification

Li,

Ishak,

Ibrahim

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In recent years, recommendation systems have become essential for businesses to enhance customer satisfaction and generate revenue in various domains, such as e-commerce and entertainment. Deep learning techniques have significantly improved the accuracy and efficiency of these systems. However, there is a lack of literature on classification in systematic review papers that summarize the latest deep-learning techniques used in recommendation systems. Moreover, certain existing review papers have either overlooked state-of-the-art techniques or restricted their coverage to a narrow spectrum of domains.To address these research gaps, we present a systematic review paper that comprehensively analyzes the literature on deep learning techniques in recommendation systems, specifically using term classification. We analyzed relevant studies published between 2018 and February 2023, examining the techniques, datasets, domains, and measurement metrics used in these studies, utilizing a thorough SLR strategy. Our review reveals that deep learning techniques, such as graph neural networks, convolutional neural networks, and recurrent neural networks, have been widely used in recommendation systems. Furthermore, our study highlights the emerging area of research in domain classification, which has shown promising results in applying deep learning techniques to domains such as social networks, e-commerce, and e-learning. Our review paper offers insights into the deep learning techniques used across different recommendation systems and provides suggestions for future research. Our review fills a critical research gap and offers a valuable resource for researchers and practitioners interested in deep learning techniques for recommendation systems. INDEX TERMSDeep learning, term classification, recommendation system, systematic review, state-ofthe-art techniques I. INTRODUCTION

show abstract

“…The user-user social interactions can also be easily turned into a graph. This property enables GNN-based recommendation system models [15][16][17] to extract collaboration signals from numerous interactions and obtain powerful node representations from high-order neighbor information.…”

Section: Introductionmentioning

confidence: 99%

SSGCL: Simple Social Recommendation with Graph Contrastive Learning

Duan,

Wang,

Zhong

2024

Mathematics

View full text Add to dashboard Cite

As user–item interaction information is typically limited, collaborative filtering (CF)-based recommender systems often suffer from the data sparsity issue. To address this issue, recent recommender systems have turned to graph neural networks (GNNs) due to their superior performance in capturing high-order relationships. Furthermore, some of these GNN-based recommendation models also attempt to incorporate other information. They either extract self-supervised signals to mitigate the data sparsity problem or employ social information to assist with learning better representations under a social recommendation setting. However, only a few methods can take full advantage of these different aspects of information. Based on some testing, we believe most of these methods are complex and redundantly designed, which may lead to sub-optimal results. In this paper, we propose SSGCL, which is a recommendation system model that utilizes both social information and self-supervised information. We design a GNN-based propagation strategy that integrates social information with interest information in a simple yet effective way to learn user–item representations for recommendations. In addition, a specially designed contrastive learning module is employed to take advantage of the self-supervised signals for a better user–item representation distribution. The contrastive learning module is jointly optimized with the recommendation module to benefit the final recommendation result. Experiments on several benchmark data sets demonstrate the significant improvement in performance achieved by our model when compared with baseline models.

show abstract

Multi-Behavior Graph Neural Networks for Recommender System

Cited by 15 publications

References 60 publications

Explicit Behavior Interaction with Heterogeneous Graph for Multi-behavior Recommendation

Explicit Behavior Interaction with Heterogeneous Graph for Multi-behavior Recommendation

Deep Learning-Based Recommendation System: Systematic Review and Classification

SSGCL: Simple Social Recommendation with Graph Contrastive Learning

Contact Info

Product

Resources

About