AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (31.4 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

MDGCN-Lt: Fair Web API Classification with Sparse and Heterogeneous Data Based on Deep GCN

Department of School of Computer Science, Qufu Normal University, Rizhao 276500, China
Shandong Provincial University Laboratory for Protected Horticulture, Weifang University of Science and Technology, Weifang 261000, China
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, China
Department of Univalsoft Joint Stock Co., Ltd., Weifang 261000, China
Show Author Information

Abstract

Developers integrate web Application Programming Interfaces (APIs) into edge applications, enabling data expansion to the edge computing area for comprehensive coverage of devices in that region. To develop edge applications, developers search API categories to select APIs that meet specific functionalities. Therefore, the accurate classification of APIs becomes critically important. However, existing approaches, as evident on platforms like programableweb.com, face significant challenges. Firstly, sparsity in API data reduces classification accuracy in works focusing on single-dimensional API information. Secondly, the multidimensional and heterogeneous structure of web APIs adds complexity to data mining tasks, requiring sophisticated techniques for effective integration and analysis of diverse data aspects. Lastly, the long-tailed distribution of API data introduces biases, compromising the fairness of classification efforts. Addressing these challenges, we propose MDGCN-Lt, an API classification approach offering flexibility in using multi-dimensional heterogeneous data. It tackles data sparsity through deep graph convolutional networks, exploring high-order feature interactions among API nodes. MDGCN-Lt employs a loss function with logit adjustment, enhancing efficiency in handling long-tail data scenarios. Empirical results affirm our approach’s superiority over existing methods.

References

[1]
S. Nguyen, C. T. Manh, K. T. Tran, T. M. Nguyen, T. T. Nguyen, K. T. Ngo, and H. D. Vo, ARIST: An effective API argument recommendation approach, J. Syst. Softw., vol. 204, p. 111786, 2023.
[2]
C. Yang, B. Xu, J. Y. Khan, G. Uddin, D. Han, Z. Yang, and D. Lo, Aspect-based API review classification: How far can pre-trained transformer model go? in Proc. 2022 IEEE Int. Conf. Software Analysis, Evolution and Reengineering (SANER ), Honolulu, HI, USA, 2022, pp. 385–395.
[3]

Z. Fan, W. Yang, F. Wu, J. Cao, and W. Shi, Serving at the edge: An edge computing service architecture based on ICN, ACM Trans. Internet Technol., vol. 22, no. 1, p. 22, 2021.

[4]

D. Wei, H. Ning, F. Shi, Y. Wan, J. Xu, S. Yang, and L. Zhu, Dataflow management in the internet of things: Sensing, control, and security, Tsinghua Science and Technology, vol. 26, no. 6, pp. 918–930, 2021.

[5]

G. Wang, J. Yu, M. Nguyen, Y. Zhang, S. Yongchareon, and Y. Han, Motif-based graph attentional neural network for web service recommendation, Knowl.-Based Syst., vol. 269, p. 110512, 2023.

[6]
T. Long, P. Chen, Y. Xia, N. Jiang, X. Wang, and M. Long, A novel fault-tolerant approach to web service composition upon the edge computing environment, in Proc. 28 th Int. Conf. Web Services, Virtual Event, 2021, pp. 15–31.
[7]

B. Xu, S. Luo, and Y. Yan, Efficient composition of semantic web services with end-to-end QoS optimization, Tsinghua Science and Technology, vol. 15, no. 6, pp. 678–686, 2010.

[8]
W. Gong, H. Wu, X. Wang, X. Zhang, Y. Wang, Y. Chen, and M. R. Khosravi, Diversified and compatible web APIs recommendation based on game theory in IoT, Digit. Commun. Netw., doi: 10.1016/j.dcan.2023.02.002.
[9]

L. Qi, Q. He, F. Chen, X. Zhang, W. Dou, and Q. Ni, Data-driven web APIs recommendation for building web applications, IEEE Trans. Big Data, vol. 8, no. 3, pp. 685–698, 2022.

[10]
X. Wang, J. Liu, X. Liu, X. Cui, and H. Wu, A novel dual-graph convolutional network based web service classification framework, in Proc. 2020 IEEE Int. Conf. Web Services (ICWS ), Beijing, China, 2020, pp. 281–288.
[11]

H. Kou, J. Xu, and L. Qi, Diversity-driven automated web API recommendation based on implicit requirements, Appl. Soft Comput., vol. 136, p. 110137, 2023.

[12]

S. H. Ali, R. A. El-Atier, K. M. Abo-Al-Ez, and A. I. Saleh, A gen-fuzzy based strategy (GFBS) for web service classification, Wirel. Pers. Commun., vol. 113, no. 4, pp. 1917–1953, 2020.

[13]

M. Hasnain, I. Ghani, S. R. Jeong, and A. Ali, Ensemble learning models for classification and selection of web services: A review, Comput. Syst. Sci. Eng., vol. 40, no. 1, pp. 327–339, 2022.

[14]

Z. Meng and Z. Shi, On rule acquisition methods for data classification in heterogeneous incomplete decision systems, Knowl.-Based Syst., vol. 193, p. 105472, 2020.

[15]

S. Jose, K. T. P. Nguyen, K. Medjaher, R. Zemouri, M. Lévesque, and A. Tahan, Fault detection and diagnostics in the context of sparse multimodal data and expert knowledge assistance: Application to hydrogenerators, Comput. Ind., vol. 151, p. 103983, 2023.

[16]

Q. Chen, T. Huang, G. Zhu, and E. Lin, A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition, Neural Netw., vol. 168, pp. 214–222, 2023.

[17]

Z. Zhu, H. Xing, and Y. Xu, Easy balanced mixing for long-tailed data, Knowl.-Based Syst., vol. 248, p. 108816, 2022.

[18]
W. Liu, Z. Wu, Y. Wang, H. Ding, F. Liu, J. Lin, and G. Lin, LCReg: Long-tailed image classification with latent categories based recognition, Pattern Recognition, vol. 145, p. 109971, 2024.
[19]
G. Petrosyan, M. P. Robillard, and R. De Mori, Discovering information explaining API types using text classification, in Proc. 2015 IEEE/ACM 37 th IEEE Int. Conf. Software Engineering, Florence, Italy, 2015, pp. 869–879.
[20]
J. Liu, Z. Tian, P. Liu, J. Jiang, and Z. Li, An approach of semantic web service classification based on Naive Bayes, in 2016 IEEE Int. Conf. Services Computing (SCC ), San Francisco, CA, USA, 2016, pp. 356–362.
[21]

S. Sharma, J. S. Lather, and M. Dave, Semantic approach for web service classification using machine learning and measures of semantic relatedness, Serv. Oriented Comput. Appl., vol. 10, no. 3, pp. 221–231, 2016.

[22]
X. Liu, S. Agarwal, C. Ding, and Q. Yu, An LDA-SVM active learning framework for web service classification, in Proc. 2016 IEEE Int. Conf. Web Services (ICWS ), San Francisco, CA, USA, 2016, pp. 49–56.
[23]
B. Cheng, S. Zhao, C. Li, and J. Chen, MISDA: Web services discovery approach based on mining interface semantics, in Proc. 2016 IEEE Int. Conf. Web Services (ICWS ), San Francisco, CA, USA, 2016, pp. 332–339.
[24]
Y. Cao, J. Liu, B. Cao, M. Shi, Y. Wen, and Z. Peng, Web services classification with topical attention based Bi-LSTM, in Proc. 15 th EAI Int. Conf. Collaborative Computing : Networking, Applications and Worksharing, London, UK, pp. 394–407.
[25]
H. Ye, B. Cao, J. Chen, J. Liu, Y. Wen, and J. Chen, A web services classification method based on GCN, in Proc. 2019 IEEE Int. Conf. Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom ), Xiamen, China, 2019, pp. 1107–1114.
[26]

K. Zhao, J. Liu, Z. Xu, X. Liu, L. Xue, Z. Xie, Y. Zhou, and X. Wang, Graph4Web: A relation-aware graph attention network for web service classification, J. Syst. Softw., vol. 190, p. 111324, 2022.

[27]
Y. Yang, N. Qamar, P. Liu, K. Grolinger, W. Wang, Z. Li, and Z. Liao, ServeNet: A deep neural network for web services classification, in Proc. 2020 IEEE Int. Conf. Web Services (ICWS ), Beijing, China, 2020, pp. 168–175.
[28]

B. Tang, M. Yan, N. Zhang, L. Xu, X. Zhang, and H. Ren, Co-attentive representation learning for web services classification, Expert Syst. Appl., vol. 180, p. 115070, 2021.

[29]
H. Huang, B. Cao, S. Liu, D. Zhou, M. Tang, and F. Xiao, A web service classification method based on graph neural network knowledge distillation, in Proc. 2022 IEEE Smartworld, Ubiquitous Intelligence & Computing, Scalable Computing & Communications, Digital Twin, Privacy Computing, Metaverse, Autonomous & Trusted Vehicles, Haikou, China, 2022, pp. 1710–1715.
[30]
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, BERT: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv: 1810.04805, 2019.
[31]
J. Gasteiger, A. Bojchevski, and S. Günnemann, Predict then propagate: Graph neural networks meet personalized PageRank, arXiv preprint arXiv: 1810.05997, 2022.
[32]
M. Chen, Z. Wei, Z. Huang, B. Ding, and Y. Li, Simple and deep graph convolutional networks, in Proc. 37 th Int. Conf. Machine Learning, Virtual, 2020, pp. 1725–1735.
[33]
A. K. Menon, S. Jayasumana, A. S. Rawat, H. Jain, A. Veit, and S. Kumar, Long-tail learning via logit adjustment, arXiv preprint arXiv: 2007.07314, 2021.
[34]

M. Liu, Z. Tu, Y. Zhu, X. Xu, Z. Wang, and Q. Z. Sheng, Data correction and evolution analysis of the ProgrammableWeb service ecosystem, J. Syst. Softw., vol. 182, p. 111066, 2021.

[35]
T. N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, arXiv preprint arXiv: 1609.02907, 2017.
[36]

B. Karlik and A. V. Olgac, Performance analysis of various activation functions in generalized MLP architectures of neural networks, Int. J. Artif. Intell. Expert Syst., vol. 1, no. 4, pp. 111–122, 2011.

[37]
Y. Hu, H. You, Z. Wang, Z. Wang, E. Zhou, and Y. Gao, Graph-MLP: Node classification without message passing in graph, arXiv preprint arXiv: 2106.04051, 2021.
[38]
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, Graph attention networks, arXiv preprint arXiv: 1710.10903, 2018.
[39]
S. Cao, W. Lu, and Q. Xu, GraRep: Learning graph representations with global structural information, in Proc. 24 th ACM Int. Conf. Information and Knowledge Management, Melbourne, Australia, 2015, pp. 891–900.
[40]
A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, Bag of tricks for efficient text classification, arXiv preprint arXiv: 1607.01759, 2016.
[41]
J. Wu, J. He, and J. Xu, DEMO-Net: Degree-specific graph neural networks for node and graph classification, in Proc. 25 th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, Anchorage, AK, USA, 2019, pp. 406–415.
Tsinghua Science and Technology
Pages 1294-1314
Cite this article:
Yan B, Zhang Y, Gong W, et al. MDGCN-Lt: Fair Web API Classification with Sparse and Heterogeneous Data Based on Deep GCN. Tsinghua Science and Technology, 2025, 30(3): 1294-1314. https://doi.org/10.26599/TST.2024.9010026

62

Views

1

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics

Received: 03 December 2023
Revised: 01 January 2024
Accepted: 24 January 2024
Published: 30 December 2024
© The Author(s) 2025.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return