A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks
Most existing recommendation models only consider single user–item interaction information, which leads to serious cold-start or data sparsity problems. In practical applications, a user’s behavior is multi-type, and different types of user behavior show different semantic information. To achieve mo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/16/9315 |
| _version_ | 1797585643392466944 |
|---|---|
| author | Ran Li Yuexin Li Jingsheng Lei Shengying Yang |
| author_facet | Ran Li Yuexin Li Jingsheng Lei Shengying Yang |
| author_sort | Ran Li |
| collection | DOAJ |
| description | Most existing recommendation models only consider single user–item interaction information, which leads to serious cold-start or data sparsity problems. In practical applications, a user’s behavior is multi-type, and different types of user behavior show different semantic information. To achieve more accurate recommendations, a major challenge comes from being able to handle heterogeneous behavior data from users more finely. To address this problem, this paper proposes a multi-behavior recommendation framework based on a graph neural network, which captures personalized semantics of specific behavior and thus distinguishes the importance of different behaviors for predicting the target behavior. Meanwhile, this model establishes dependency relationships among different types of interaction behaviors under the graph-based information transfer network, and the graph convolutional network is further used to capture the high-order complexity of interaction graphs. The experimental results of three benchmark datasets show that the proposed graph-based multi-behavior recommendation model displays significant improvements in recommendation accuracy compared to the baseline method. |
| first_indexed | 2024-03-11T00:09:59Z |
| format | Article |
| id | doaj.art-d853b437b2324cf79650a3f5427d95b9 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T00:09:59Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d853b437b2324cf79650a3f5427d95b92023-11-19T00:07:50ZengMDPI AGApplied Sciences2076-34172023-08-011316931510.3390/app13169315A Multi-Behavior Recommendation Method for Users Based on Graph Neural NetworksRan Li0Yuexin Li1Jingsheng Lei2Shengying Yang3Guizhou Power Grid Company Limited, Guiyang 550002, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaMost existing recommendation models only consider single user–item interaction information, which leads to serious cold-start or data sparsity problems. In practical applications, a user’s behavior is multi-type, and different types of user behavior show different semantic information. To achieve more accurate recommendations, a major challenge comes from being able to handle heterogeneous behavior data from users more finely. To address this problem, this paper proposes a multi-behavior recommendation framework based on a graph neural network, which captures personalized semantics of specific behavior and thus distinguishes the importance of different behaviors for predicting the target behavior. Meanwhile, this model establishes dependency relationships among different types of interaction behaviors under the graph-based information transfer network, and the graph convolutional network is further used to capture the high-order complexity of interaction graphs. The experimental results of three benchmark datasets show that the proposed graph-based multi-behavior recommendation model displays significant improvements in recommendation accuracy compared to the baseline method.https://www.mdpi.com/2076-3417/13/16/9315multi-behavior recommendationgraph convolutional networkhigher-order complexitygraph information transfer network |
| spellingShingle | Ran Li Yuexin Li Jingsheng Lei Shengying Yang A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks Applied Sciences multi-behavior recommendation graph convolutional network higher-order complexity graph information transfer network |
| title | A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks |
| title_full | A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks |
| title_fullStr | A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks |
| title_full_unstemmed | A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks |
| title_short | A Multi-Behavior Recommendation Method for Users Based on Graph Neural Networks |
| title_sort | multi behavior recommendation method for users based on graph neural networks |
| topic | multi-behavior recommendation graph convolutional network higher-order complexity graph information transfer network |
| url | https://www.mdpi.com/2076-3417/13/16/9315 |
| work_keys_str_mv | AT ranli amultibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT yuexinli amultibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT jingshenglei amultibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT shengyingyang amultibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT ranli multibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT yuexinli multibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT jingshenglei multibehaviorrecommendationmethodforusersbasedongraphneuralnetworks AT shengyingyang multibehaviorrecommendationmethodforusersbasedongraphneuralnetworks |