Motif-based Graph Attention Network for Web Service Recommendation

Zhang, Yuqi; Yu, Jian; Ruan, Ji; Wang, Nancy; Madanian, Samaneh; Wang, Guiling

doi:10.1145/3579375.3579393

Cited by 2 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GCN. 21 GCN uses graph structure information to aggregate node features to generate target node feature representations. The essence of GCN is to obtain the spatial structure features of the topology map.…”

Section: Baselinesmentioning

confidence: 99%

“…GNN 21 is widely used in service recommendation since the service network can learn more effective features and potential information. Among them, Zhang et al 22 apply bilinear graph neural network (BGNN) to Web service classification, modeling the interaction information between neighbor service nodes.…”

Section: Related Workmentioning

confidence: 99%

“…These methods can effectively achieve service classification. Wang et al 21 apply graph attention neural network to Web service recommendation. In order to obtain more structural subgraph information, they utilize a motif‐based attention mechanism to mine high‐order interaction information of various motifs and propose a Motif‐based graph attention network service recommendation model.…”

Section: Related Workmentioning

confidence: 99%

“…GNN models are used as the baselines to compare with the proposed method. We choose six different GNN models as teacher models, as shown below: GCN 21 . GCN uses graph structure information to aggregate node features to generate target node feature representations.…”

Section: Experiments and Analysismentioning

confidence: 99%

See 3 more Smart Citations

Knowledge distillation representation and DCNMIX quality prediction‐based Web service recommendation

Cao,

Huang,

Liu

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryWeb service recommendation as an emerging topic attracts increasing attention due to its important practical significance. As the number of available Web services continues to grow, users face the challenge of searching the most suitable services that meet their specific needs. Quality of service (QoS)‐based service recommendation becomes a popular approach to address this issue. However, existing QoS‐based service recommendation methods are inability to effectively capture valuable content and structural information from services. These methods often rely solely on low‐order explicit feature intersections in QoS information, do not fully utilize the high‐order implicit feature intersections, and ignore the rich semantic information existing in service descriptions and user preferences. To address this problem, this paper proposes a Web service recommendation method via combining knowledge distillation representation and DCNMIX quality prediction. This method combines content‐based and structure‐based service classification and service prediction based on multi‐dimensional service quality information. First, it builds a service relationship network using semantic features extracted from service descriptions. Second, it designs a graph neural network knowledge distillation framework. The teacher model extracts the knowledge of the graph neural network model, and the student model learns the structure‐based and feature‐based prior knowledge of the service relationship network. Then the student model is used to learn the knowledge of the teacher model, classify Web services, and obtain service representations. Finally, based on service representations and multi‐dimensional QoS information, it exploits the DCNMIX model to learn the explicit and implicit features intersections of Web services and obtain the prediction score and ranking of Web services. The experimental results on the ProgrammableWeb dataset show that the proposed method outperforms the state‐of‐the‐art baselines in terms of Recall, F1, Logloss, and AUC_ROC.

show abstract

Section: Baselinesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Experiments and Analysismentioning

confidence: 99%

See 2 more Smart Citations