Graph4Web: A relation-aware graph attention network for web service classification

Zhao, Kunsong; Liu, Jin; Zhou, Xu; Liu, Xiao; Xue, Lei; Xie, Zheng; Zhou, Yuxuan; Wang, Xin

doi:10.1016/j.jss.2022.111324

Cited by 16 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results can be explained by the ability of BNs to visually represent the dependencies between the different elements of a WS. Which is a facilitating element (Zhao et al, 2022) in the particular case of Service composition.…”

Section: Summary and Discussionmentioning

confidence: 99%

“…Web services (WSs) have revolutionized software development practices. De ned as "software components that were self-described, loosely coupled, and easily integrated with one another" (Driss et al, 2022), WSs are present in practically all elds (Bouguettaya et al, 2017;Zhao et al, 2022). This success is fueled, among other things, by the possibilities offered by WSs in terms of cost reduction, ease of reuse and operational e ciency (Papazoglou et al, 2008;Zhao et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of bayesian networks in web services: a scoping review

Guinhouya¹

2023

Preprint

View full text Add to dashboard Cite

Context. Web services (WSs) are the preferred approach in realizing the service-oriented computing paradigm. However, this comes with challenges like complexity and uncertainty. Bayesian networks (BNs) are one of the techniques used to deal with these challenges. Objective. This study aims to determine and describe what is known about the use of BNs in WSs research. Methods. Using the scoping review method, we selected 69 (among the 532 identified) articles published on the subject (2001-2021). These articles were classified by research themes (What), research objectives (Why), and the types of bayesian network used (How). Results. The research themes explored are, in order of importance, Service composition, Service management, and Service engineering. In terms of research objectives, the articles mainly focused on Prediction, Description, and Prescription. Finally, the types of BNs used are Basic, Combined, and Extended BNs. Conclusion. This review offers a first structured picture of the use of BNs in WSs. Its results can help researchers and practitioners interested in the subject.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of bayesian networks in web services: a scoping review

Guinhouya¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, due to the powerful ability to model dependency relationships within a graph, GNNs have been widely applied in various deep learning tasks and applications 55–57 . Therefore, our model employs GCN to learn dependency information when encoding event types, as mentioned in subsection 4.3.…”

Section: Methodsmentioning

confidence: 99%

“…Recently, due to the powerful ability to model dependency relationships within a graph, GNNs have been widely applied in various deep learning tasks and applications. [55][56][57] Therefore, our model employs GCN to learn dependency information when encoding event types, as mentioned in subsection 4.3. Moreover, due to the significant advantages of hyperbolic space in capturing hierarchical structures, we have also applied hyperbolic space in our model to learn the hierarchical relationships among event types.…”

Section: Ablation Studymentioning

confidence: 99%

HyperED: A hierarchy‐aware network based on hyperbolic geometry for event detection

Zhang,

Xie,

Liu

et al. 2024

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well‐organized with a hierarchical structure in real‐world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, the most existing methods perform event detection in Euclidean space, which cannot adequately represent hierarchical relationships. To address these issues, we propose a novel event detection network HyperED which embeds the event context and types in Poincaré ball of hyperbolic geometry to help learn hierarchical features between events. Specifically, for the event detection context, we first leverage the pre‐trained BERT or BiLSTM in Euclidean space to learn the semantic features of ED sentences. Meanwhile, to make full use of the dependency knowledge, a GNN‐based model is applied when encoding event types to learn the correlations between events. Then we use a simple neural‐based transformation to project the embeddings into the Poincaré ball to capture hierarchical features, and a distance score in hyperbolic space is computed for prediction. The experiments on MAVEN and ACE 2005 datasets indicate the effectiveness of the HyperED model and prove the natural advantages of hyperbolic spaces in expressing hierarchies in an intuitive way.

show abstract

“…Structural feature-based service classification approaches focus on mining the structural relationships of Web services (Gao et al , 2022), such as service composition (Liang et al , 2022), tag sharing (Shi et al , 2021) and textual syntactic structure (Zhao et al , 2022). These relationships are represented as graphs, and structural features are extracted by network representation algorithms such as Node2vec (Grover and Leskovec, 2016), DeepWalk (Perozzi et al , 2014), GCN, GNN (Zhou et al , 2020) and other neural network-based graph embedding approaches.…”

Section: Related Workmentioning

confidence: 99%

LCPCWSC: a Web service classification approach based on label confusion and priori correction

Xue,

Zhang

2024

IJWIS

View full text Add to dashboard Cite

Purpose With the increasing number of Web services, correct and efficient classification of Web services is crucial to improve the efficiency of service discovery. However, existing Web service classification approaches ignore the class overlap in Web services, resulting in poor accuracy of classification in practice. This paper aims to provide an approach to address this issue. Design/methodology/approach This paper proposes a label confusion and priori correction-based Web service classification approach. First, functional semantic representations of Web services descriptions are obtained based on BERT. Then, the ability of the model is enhanced to recognize and classify overlapping instances by using label confusion learning techniques; Finally, the predictive results are corrected based on the label prior distribution to further improve service classification effectiveness. Findings Experiments based on the ProgrammableWeb data set show that the proposed model demonstrates 4.3%, 3.2% and 1% improvement in Macro-F1 value compared to the ServeNet-BERT, BERT-DPCNN and CARL-NET, respectively. Originality/value This paper proposes a Web service classification approach for the overlapping categories of Web services and improve the accuracy of Web services classification.

show abstract

Graph4Web: A relation-aware graph attention network for web service classification

Cited by 16 publications

References 31 publications

Application of bayesian networks in web services: a scoping review

Application of bayesian networks in web services: a scoping review

HyperED: A hierarchy‐aware network based on hyperbolic geometry for event detection

LCPCWSC: a Web service classification approach based on label confusion and priori correction

Contact Info

Product

Resources

About