Accurately Predicting Quality of Services in IoT via Using Self-Attention Representation and Deep Factorization Machines

Tang, Mingdong; Tang, Wenyu; Xie, Fei

doi:10.1109/tits.2023.3279412

Cited by 5 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The attention mechanism (Vaswani et al, 2017) is a mechanism that extracts important information from a large amount of information by simulating the way the human brain processes information overload, which relies less on external information and focuses more on capturing the internal relevance of data or features. The use of the Self-Attentive Mechanism to dynamically adjust the weights of different features of the service data can enhance the extraction of features with high contribution to the service recommendation results and make the model more focused on the classification of features with high contribution (Tang et al, 2023).…”

Section: Multi-head Self-attention Representationmentioning

confidence: 99%

A Service Recommendation Algorithm Based on Self-Attention Mechanism and DeepFM

Deng,

Guo,

Zheng

2023

International Journal of Web Services Research

View full text Add to dashboard Cite

This article proposes a recommendation model based on self-attention mechanism and DeepFM service, the model is SelfA-DeepFM. The method firstly constructs the service network with DTc-LDA model to mine the potential relationship between Mashup and API, which not only fully considers the text attributes but also combines the network structure information to effectively mitigate the sparsity of the service data. Secondly, service clustering to obtain numerical feature similarities. Finally, the self-attention mechanism is used to capture the different importance of feature interactions, and the DeepFM model is used to mine the complex interaction information between multidimensional features to predict and rank the quality score of API services to recommend suitable APIs. To verify the performance of the model, the authors use the real data crawled from the ProgrammableWeb platform to conduct multiple groups of experiments. The experimental results show that the model significantly improves the accuracy of service recommendation.

show abstract

Section: Multi-head Self-attention Representationmentioning

confidence: 99%