Modelling High-Order Social Relations for Item Recommendation

Yang, Liu; Chen, Liang; He, Xiangnan; Peng, Jiaying; Zheng, Zibin; Tang, Jie

doi:10.1109/tkde.2020.3039463

Cited by 66 publications

(35 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the increasing number of mobile phone users, social recommendation has become the most popular way to connect users and items. The general definition of the social recommendation model [13] is as follows:…”

Section: Recommender Systemmentioning

confidence: 99%

See 1 more Smart Citation

FSCR: A Deep Social Recommendation Model for Misleading Information

Zhang

Yang

2021

Information

View full text Add to dashboard Cite

The popularity of intelligent terminals and a variety of applications have led to the explosive growth of information on the Internet. Some of the information is real, some is not real, and may mislead people’s behaviors. Misleading information refers to false information made up by some malicious marketer to create panic and seek benefits. In particular, when emergency events break out, many users may be misled by the misleading information on the Internet, which further leads them to buy things that are not in line with their actual needs. We call this kind of human activity ‘emergency consumption’, which not only fails to reflect users’ true interests but also causes the phenomenon of user preference deviation, and thus lowers the accuracy of the personal recommender system. Although traditional recommendation models have proven useful in capturing users’ general interests from user–item interaction records, learning to predict user interest accurately is still a challenging problem due to the uncertainty inherent in user behavior and the limited information provided by user–item interaction records. In addition, to deal with the misleading information, we divide user information into two types, namely explicit preference information (explicit comments or ratings) and user side information (which can show users’ real interests and will not be easily affected by misleading information), and then we create a deep social recommendation model which fuses user side information called FSCR. The FSCR model is significantly better than existing baseline models in terms of rating prediction and system robustness, especially in the face of misleading information; it can effectively identify the misleading users and complete the task of rating prediction well.

show abstract

Section: Recommender Systemmentioning

confidence: 99%

“…To show that our model has better performance when facing misleading information, we use two widely used metrics: Root Mean Square Error (RMSE) in Equation 12and Mean Absolute Error (MAE) in Equation (13). y p is the prediction score; y a is the true score; n is the number of users.…”

Section: Evaluation Metricsmentioning

confidence: 99%

FSCR: A Deep Social Recommendation Model for Misleading Information

Zhang

Yang

2021

Information

View full text Add to dashboard Cite

show abstract

“…Compared with the study of explicit trust features, we focus more on the implicit trust behavior between users and trust users, and study the regular patterns between them. The formula (11) shows that in the ATGCN model, the balance factor affects the loss of the two parts, thus balancing the proportion of the two parts, that is, if the balance factor γ increases, the model will be more affected by the implicit trust attributes, and vice versa.…”

Section: ) the Influence Of Balance Factormentioning

confidence: 99%

“…In our early work, we focused on describing the explicit relationship between users and trust friends. In recent years, researchers explicitly describe the social relationship between users and trust friends [27], [41], [42], such as Liu et al [26] built a high-order convolution network based on the attention mechanism, which can make the information of trusted users spread in a wider range and make users have more trust users. Researchers attempted to found their commonness in many algorithms that describe the explicit relationship between users and trust users, so as to extract more representative explicit social features.…”

Section: Related Workmentioning

confidence: 99%

“…Some studies attempt to alleviate the noise problem, divide trust data into more fine-grained classes, consider only reliable relationships, for example, Kim et al [9] proposed a noise reduction algorithm, by using tripartite heterogeneous relationships, extracting explicit trust features of users, and then minimize the impact of noise. Meanwhile, some studies [10], [11] attempt to focus on potential but reliable social relationships, these relationships are not direct connections, but users have similarities in some ways, these relationships are also called implicit trust relationships. Briefly, the idea to reduce the noise in trust information is to add reliable social connections or filter unreliable social connections [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Learning User Implicit Trust Behavior Based on Graph Convolution Network

Seng

Lai

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In the existing social recommendation algorithms, the performance of the algorithms is bothered by the problem of noise and sparsity in social information. In the past few years, researchers have usually focused on solving noise problem or sparse problem, but ignored a key problem, that is if only solving the noise problem, the sparse problem will become more serious, similarly, if only solving the sparse problem, the noise problem will become more serious. Recently, a few studies attempt to solve both noise and sparse problems, usually using explicit trust features to filter trust information and generate implicit trust friends, but this will depend heavily on the quality of explicit trust features. Therefore, in this paper, we propose an adaptive algorithm based on graph convolution network, The main idea is to learn users' implicit trust behavior adaptively. Briefly, we use Jaccard similarity coefficient to filter out unnecessary trust information, the reliable trust information will be the users' trust attributes, then put into the graph convolution network, because of the good feature extraction ability of graph convolution network, we can use adaptive network to learn implicit trust features based on users' features, the trust features can infer the trust attributes for all users. In order to achieve the best effect of learning, we use iterative repetition of the above process, to mining the implicit influence of user trust behavior, so as to alleviate noise and sparsity problems. Experimental result shows that, on three open datasets: LastFM, Douban and Gowalla, the recommendation performance is improved, which proves the effectiveness of the algorithm.

show abstract