[1]ZHU Linli,HUA Gang,GAO Wei.Two classes of LOO uniform stability and generalization bounds of ontology learning algorithm[J].CAAI Transactions on Intelligent Systems,2022,17(3):471-479.[doi:10.11992/tis.202101015]
Copy

Two classes of LOO uniform stability and generalization bounds of ontology learning algorithm

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 17 Number of periods: 2022 3 Page number: 471-479 Column: 学术论文—机器学习 Public date: 2022-05-05
Title:
Two classes of LOO uniform stability and generalization bounds of ontology learning algorithm
Author(s):
ZHU Linli1; 2;  HUA Gang1;  GAO Wei3
1. School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China;
2. School of Computer Engineering, Jiangsu University of Technology, Changzhou 213001, China;
3. School of Information, Yunnan Normal University, Kunming 650500, China
Keywords:
ontology; machine learning; stability; generalized bound; ontology data-dependent function; ontology sample dependent hypothesis set; Rademacher complexity; empirical Rademacher complexity
CLC:
TP391
DOI:
10.11992/tis.202101015
Abstract:
Recently, with deepening ontology research, efforts have been made to apply various machine-learning methods to ontology similarity calculations and mapping acquisitions. Stability is a necessary condition for ontology-learning algorithms. It requires that the optimal solution of the algorithm does not undergo major changes due to small adjustments to the ontology samples; thus, it essentially reflects the usability of the algorithm. In this study, we investigated the effect of deleting an ontology sample point on the difference between the expected and empirical errors of the ontology-learning algorithm. In two settings of the ontology-learning algorithm—uniform stability and hypothetical space uniform stability—obtained using statistical learning theory, the corresponding upper bound estimates of generalized bounds are determined.
References:
[1] SKALLE P, AAMODT A. Petrol 18 946: downhole failures revealed through ontology engineering[J]. Journal of petroleum science and engineering, 2020, 191: 107188.
[2] SOBRAL T, GALV?O T, BORGES J. An ontology-based approach to knowledge-assisted integration and visualization of urban mobility data[J]. Expert systems with applications, 2020, 150: 113260.
[3] AL-SAYED M M, HASSAN H A, OMARA F A. CloudFNF: an ontology structure for functional and non-functional features of cloud services[J]. Journal of parallel and distributed computing, 2020, 141: 143–173.
[4] TEBES G, PEPPINO D, BECKER P, et al. Analyzing and documenting the systematic review results of software testing ontologies[J]. Information and software technology, 2020, 123: 106298.
[5] PRADEEP D, SUNDAR C. QAOC: novel query analysis and ontology-based clustering for data management in Hadoop[J]. Future generation computer systems, 2020, 108: 849–860.
[6] HEMA A M, KUPPUSAMY K. A novel trust-based privacy preservation framework for service handling via ontology service ranking[J]. Wireless personal communications, 2020, 112(3): 1339–1354.
[7] MESSAOUDI R, MTIBAA A, VACAVANT A, et al. Ontologies for liver diseases representation: a systematic literature review[J]. Journal of digital imaging, 2020, 33(3): 563–573.
[8] MANTOVANI A, PIANA F, LOMBARDO V. Ontology-driven representation of knowledge for geological maps[J] Computers and geosciences, 2020, 139: 104446.
[9] ABEYSINGHE R, HINDERER III E W, MOSELEY H N B, et al. SSIF: subsumption-based sub-term inference framework to audit gene ontology[J]. Bioinformatics, 2020, 36(10): 3207–3214.
[10] KOSSMANN M, SAMHAN A, ODEH M, et al. Extending the scope of configuration management for the development and life cycle support of systems of systems-an ontology-driven framework applied to the enceladus submarine exploration lander[J]. Systems engineering, 2020, 23(3): 366–391.
[11] ZHU Linli, HUA Gang, ASLAM A. Ontology learning algorithm using weak functions[J]. Open physics, 2018, 16(1): 910–916.
[12] GAO Wei, ZHANG Yunqing, GUIRAO J L G, et al. A discrete dynamics approach to sparse calculation and applied in ontology science[J]. Journal of difference equations and applications, 2019, 25(9/10): 1239–1254.
[13] ZHU Linli, HUA Gang, ZAFAR S, et al. Fundamental ideas and mathematical basis of ontology learning algorithm[J]. Journal of intelligent and fuzzy systems, 2018, 35(4): 4503–4516.
[14] GAO Wei, GUIRAO J L G, BASAVANAGOUD B, et al. Partial multi-dividing ontology learning algorithm[J]. Information sciences, 2018, 467: 35–58.
[15] 朱林立, 华钢, 高炜. 决定图框架下本体学习算法的稳定性分析[J]. 计算机科学, 2020, 47(5): 43–50
ZHU Linli, HUA Gang, GAO Wei. Stability analysis of ontology learning algorithm in decision graph setting[J]. Computer science, 2020, 47(5): 43–50
[16] ZHU Linli, YU Pan, FARAHANI M R, et al. Magnitude preserving based ontology regularization algorithm[J]. Journal of intelligent and fuzzy systems, 2017, 33(5): 3113–3122.
[17] ZHU Linli, YU Pan, JAMIL M K, et al. Boosting based ontology sparse vector computation approach[J]. Engineering letters, 2017, 25(4): 406–415.
[18] ZHU Linli, YU Pan, FARAHANI M R, et al. Theoretical characteristics on scoring function in multi-dividing setting[J]. IAENG international journal of applied mathematics, 2017, 47(1): 28–36.
[19] ZHU Linli, TAO Weige, MIN Xiaozhong, et al. Theoretical characteristics of ontology learning algorithm in multi-dividing setting[J]. IAENG international journal of computer science, 2016, 43(2): 184–191.
[20] GAO Wei, XU Tianwei. Stability analysis of learning algorithms for ontology similarity computation[J]. Abstract and applied analysis, 2013, 2013: 174802.
[21] GAO W, ZHANG Y G, XU T W, et al. Analysis for learning a similarity function with ontology applications[J]. Journal of information and computational science, 2012, 17(9): 5311–5318.
[22] BASSILY R, NISSIM K, SMITH A, et al. Algorithmic stability for adaptive data analysis[C]//Proceedings of the Forty-Eighth Annual ACM Symposium on Theory of Computing. Cambridge: ACM, 2016: 1046–1059.
[23] STEINKE T, ULLMAN J. Subgaussian tail bounds via stability arguments[EB/OL](2017–04–21)[2021–01–09]https://arxiv.org/abs/1701.03493v2.
[24] MCDIARMID C. On the method of bounded differences[M]//SIEMONS J. Surveys in Combinatorics, 1989: Invited Papers at the Twelfth British Combinatorial Conference. Cambridge: Cambridge University Press, 1989: 148–188.
[25] WALLSTROM T C. On the application of McDiarmid’s inequality to complex systems[J]. SIAM-ASA journal on uncertainty quantification, 2017, 5(1): 240–245.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems