NAFM: Neural and Attentional Factorization Machine for Web API Recommendation

Kang, Guosheng; Liu, Jianxun; Cao, Buqing; Cao, Manliang

doi:10.1109/icws49710.2020.00050

Cited by 26 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…40,41 However, QoS information is difficult to collect, and QoS values change over time and are subject to the network environment, QoS-based approaches are not practical. 42 As for the functionality based approaches, there are still some obvious drawbacks: (1) the keyword order and context information between keywords, which are essential to fully characterize services functional semantics. (2) The importance of different keywords should be discriminated when training the service classification model, which are essential to fully characterize services functional semantics.…”

Section: Related Workmentioning

confidence: 99%

“…As for the QoS‐based approaches, they are especially useful for QoS‐aware Web service selection, 34‐36 service composition, 37‐39 and service recommendation 40,41 . However, QoS information is difficult to collect, and QoS values change over time and are subject to the network environment, QoS‐based approaches are not practical 42 . As for the functionality based approaches, there are still some obvious drawbacks: (1) the keyword order and context information between keywords, which are essential to fully characterize services functional semantics.…”

Section: Related Workmentioning

confidence: 99%

“…Web APIs (also called Web services in this paper) with different functionalities can be composed to generate novel and value‐added services. Inspired by the advantages of Mashup technology and the economic benefits of Mashups, some Mashup tools and platforms have emerged on the Internet, such as WireCloud , Linked Widgets , and ProgrammableWeb 3 . These tools and platforms accelerate the prevalence of Mashup applications due to the low barriers to access and develop.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tatt‐BiLSTM: Web service classification with topical attention‐based BiLSTM

Kang

Xiao

Liu

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

With the rapid growth of the number of Web services on the Internet, how to classify Web services correctly and efficiently become particularly important in service management tasks, such as service discovery, service selection, service ranking, and service recommendation. Existing functionality-based service classification techniques have some drawbacks: (1) the keyword order and context information are not considered; (2) the embedding features of keywords are taken as equal importance to learn the classification model; (3) the topic number is hard to determine manually. Due to these drawbacks, the accuracy of service classification needs to be improved further. At present, deep learning techniques show the strong power in modeling complex and nonlinear function relationship. Thus, to address the problems above, this paper exploits attention mechanism to combine the local implicit state vector of Bidirectional Long Short-Term Memory Network (BiLSTM) and the global hierarchical Dirichlet process (HDP) topic vector, and proposes a Web service classification approach with topical attention-based BiLSTM. Specifically, BiLSTM is used to automatically learn the keyword feature representations of Web services. Then, the topic vectors of Web service documents are obtained with HDP by offline training, and topic attention mechanism is adopted to strengthen the feature representation by discriminating the importance or weight of different keywords in Web service documents. Finally, the enhanced Web service feature representation is used as the input of a softmax neural network layer to perform the classification prediction for Web services. Extensive experiments are conducted to validate the effectiveness of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tatt‐BiLSTM: Web service classification with topical attention‐based BiLSTM

Kang

Xiao

Liu

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is computationally expensive to train deep neural networks (DNNs) on an ample input feature space, requiring many parameters. The embedding layer of the FNN(Factorization-Machine-assisted Neural Network) ( He & Chua, 2017 ; Kang et al, 2020 ) is a supervised-learning Factorization machine, which efficiently decreases the dimension from extra features to dense continuous elements, as opposed to the Deep Crossing. Using pre-trained training methods to complete the embedding layer is practical engineering training, which reduces the strength of the deep learning model and training instability.…”

Section: Literature Reviewmentioning

confidence: 99%

An adaptive hybrid XdeepFM based deep Interest network model for click-through rate prediction system

Lu¹,

Li²,

Yang³

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Recent advances in communication enable individuals to use phones and computers to access information on the web. E-commerce has seen rapid development, e.g., Alibaba has nearly 12 hundred million customers in China. Click-Through Rate (CTR) forecasting is a primary task in the e-commerce advertisement system. From the traditional Logistic Regression algorithm to the latest popular deep neural network methods that follow a similar embedding and MLP, several algorithms are used to predict CTR. This research proposes a hybrid model combining the Deep Interest Network (DIN) and eXtreme Deep Factorization Machine (xDeepFM) to perform CTR prediction robustly. The cores of DIN and xDeepFM are attention and feature cross, respectively. DIN follows an adaptive local activation unit that incorporates the attention mechanism to adaptively learn user interest from historical behaviors related to specific advertisements. xDeepFM further includes a critical part, a Compressed Interactions Network (CIN), aiming to generate feature interactions at a vectorwise level implicitly. Furthermore, a CIN, plain DNN, and a linear part are combined into one unified model to form xDeepFM. The proposed end-to-end hybrid model is a parallel ensemble of models via multilayer perceptron. CIN and xDeepFM are trained in parallel, and their output is fed into a multilayer perceptron. We used the e-commerce Alibaba dataset with the focal loss as the loss function for experimental evaluation through online complex example mining (OHEM) in the training process. The experimental result indicates that the proposed hybrid model has better performance than other models.

show abstract

“…Many Web services share the same or similar functionality but provide different QoS (Quality of Service) [1]. With SOA (Service Oriented Architecture) techniques, the coarse-grained, loosely coupled Web services can be composed into complex applications or software systems [2]. The process of composing different Web services is an optimization problem of the global QoS.…”

Section: Introductionmentioning

confidence: 99%

QoS-Centric Web service Recommendation with Personalized Diversity

Kang

Liang

Liu

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

With the popularity and widespread adoption of SOA (Service Orient Architecture), the number of Web services has increased exponentially on the Internet. Meanwhile, as the cost of Internet applications decreases, users tend to use online Web services for their daily business and software development needs. Under such a background, recommending desirable Web services to users which meet users’ personalized QoS (Quality of Service) requirements becomes a challenging research issue owing to the QoS preference is usually hard to provide for users, i.e., QoS preference is uncertain. To solve the problem, some recent works try to recommend QoS-diversified services to enhance the probability of fulfilling the user’s latent QoS preferences. However, the former QoS-diversified service recommendation methods recommend services with a uniform diversity degree for different users, while the diversified preference requirements are not considered. To this end, this paper proposes to mine a user’s diversity preference from the user’s service invocation history and provides a Web service recommendation algorithm, named personalized DPP (Personalized Determinantal Point Process), through which a personalized service recommendation list with preferred diversity is generated for the user. Comprehensive experiment results show that the proposed approach can provide personalized and diversified Web services on the premise of ensuring the overall accuracy of the recommendation results.

show abstract

NAFM: Neural and Attentional Factorization Machine for Web API Recommendation

Cited by 26 publications

References 22 publications

Tatt‐BiLSTM: Web service classification with topical attention‐based BiLSTM

Tatt‐BiLSTM: Web service classification with topical attention‐based BiLSTM

An adaptive hybrid XdeepFM based deep Interest network model for click-through rate prediction system

QoS-Centric Web service Recommendation with Personalized Diversity

Contact Info

Product

Resources

About