Outlier-Resilient Web Service QoS Prediction

Ye, Fanghua; Lin, Zhiwei; Chen, Chuan; Zheng, Zibin; Huang, Hong

doi:10.1145/3442381.3449938

Cited by 29 publications

(18 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IM ) measures the degree of approximation between Q and U IM S T IM , reg denotes the regularization term to avoid over-fitting. Here we utilize the Cauchy loss [31] as the measurement of the discrepancy between the observed QoS values and the product of two implicit feature matrix, because it is more robust to outliers. Cauchy loss is shown as follows where γ is constant.…”

Section: Implicit Feature Extractionmentioning

confidence: 99%

QoS prediction in intelligent edge computing based on feature learning

et al. 2023

View full text Add to dashboard Cite

With the development of 5G and 6G, more computing and network resources on edge nodes are deployed close to the terminal. Meanwhile, the number of smart devices and intelligent services has grown significantly, which makes it difficult for users to choose a suitable service. The rich contextual information plays an important role in the prediction of service quality. In this paper, we propose a quality of service(QoS) prediction approach based on feature learning, the contextual information represented as the explicit features and underlying relationship hidden in the implicit features are fully considered. Then, the multi-head self-attention mechanism is used in the interacting layer to determine which features should be combined to form meaningful high-order features interaction. We have implemented our proposed approach with experiments based on real-world datasets. Experimental results show that our approach achieved a better performance of service QoS prediction in an intelligent edge computing environment for future communication.

show abstract

Section: Implicit Feature Extractionmentioning

confidence: 99%

QoS prediction in intelligent edge computing based on feature learning

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Wu et al [26] proposed a universal deep neural model (DNM) for making multiple attributes QoS prediction with contexts.Otherwise, Wang et al [27] suggest a hidden-state-aware network (HSA-Net) abstract the initialized hidden state by fusing the known information, Zhou et al [28] propose two universal spatio-temporal context-aware collaborative neural models (STCA-1 and STCA-2) to make QoS prediction by considering invocation time and multiple spatial features both of service-side and user-side. Ye et al [29] propose an outlier-resilient QoS prediction method to take outliers into consideration.…”

Section: Related Workmentioning

confidence: 99%

“…We evaluate the proposed HGN2HIA method's QoS prediction performance by utilizing the WS-Dream public data set [29], [30], including 1,974,675 real QoS values, such as response time between 339 users and 5,825 Web services. The dataset also provides user location information, such as the user's country and autonomous region.…”

Section: Experiments a Datasetsmentioning

confidence: 99%

QoS Prediction of Web Services Based on a Two-Level Heterogeneous Graph Attention Network

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Quality of Service (QoS) prediction for Web services is a hot research topic in the field of services computing. Recently, representation learning of heterogeneous networks has attracted much attention, and specifically the relationship between users and services, as a typical heterogeneous network in which heterogeneity and rich semantic information provide a new perspective for QoS prediction. This paper proposes a novel QoS Prediction scheme based on a heterogeneous graph attention network. Our method first unitizes the user's location information to construct an attributed user-service network. Then, considering the difference between nodes and links in the latter network, we model a heterogeneous graph neural network based on a hierarchical attention machine (HGN2HIA) that includes node-and semanticlevel attentions. Specifically, node-level attention aims to learn the importance between a node and its meta-path-based neighbors, while semantic-level attention learns the importance of different meta-paths. Finally, user embedding will be generated by aggregating features from meta-path-based neighbors in a hierarchical manner, used for QoS prediction. Experimental results on the public WS-Dream dataset demonstrate the superior performance of the proposed model over the current state-of-the-art methods, with NMAE and RMSE metrics reduced by at least 2.56% and 1.3%, respectively. Furthermore, the experimental results highlight that node-level attention contributes more than semantic-level. Overall, we demonstrate that introducing these attention levels improves the QoS prediction performance.

show abstract

“…Quality-of-Service (QoS) represents non-functional attributes of Web services, such as response time, throughput, availability, and reliability [2]. Since there are many Web services with similar functions on the network, investigating non-functional QoS attributes becomes a major concern for service selection [3], [4]. In practice, it is not easy to obtain the QoS values of all candidate services.…”

Section: Introductionmentioning

confidence: 99%

“…Matrix factorization (MF) is arguably the most popular model-based collaborative filtering technique for QoS prediction [8], [9]. MF attempts to capture the interaction between users and services [10], [11], which factorizes the high-rank user-service matrix into two low-rank feature matrices [1], [3], and the inner product of the feature matrices represents the predicted QoS values of services observed by users. In addition to the user-service interaction, there are many factors unrelated to the interaction in the real-world prediciton.…”

Section: Introductionmentioning

confidence: 99%

Collaborative Web Service Quality Prediction via Network Biased Matrix Factorization

Zhong¹,

Du²,

Chuang³

et al. 2022

Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Facing a large number of candidate Web service with the same function, user wishes to get the most appropriate one. Quality-of-Service (QoS) which represents non-functional attributes of Web services, has become a major concern for choosing service. But it is time-consuming and resource-consuming to assess all the QoS values by invoking candidate services one by one. Thus, QoS prediction is considered an effective method to obtain QoS information. Although most of QoS prediction methods claim be able to capture the interaction between users and services, few of them take account non-interaction factors, especially the factors arising from the network environment. In this paper, the non-interaction factors from the network environment are referred as network bias, and a network biased matrix factorization (NBMF) method is proposed for QoS prediction. The method packages network bias into a linear regression model and puts the user-service interaction into a matrix factorization model, which is more sophisticated in adapting diversified circumstance, particularly in complex network environment. In addition, extensive experiments are conduct on real-world QoS dataset, and the result prove that the NBMF method achieves better performance than other state-ofthe-art methods.

show abstract

Outlier-Resilient Web Service QoS Prediction

Cited by 29 publications

References 70 publications

QoS prediction in intelligent edge computing based on feature learning

QoS prediction in intelligent edge computing based on feature learning

QoS Prediction of Web Services Based on a Two-Level Heterogeneous Graph Attention Network

Collaborative Web Service Quality Prediction via Network Biased Matrix Factorization

Contact Info

Product

Resources

About