Abstract
The scalability issue has always been a bottleneck for formal concept analysis (FCA) since the number of formal concepts is possibly exponential in the formal context. Motivated by the need to handle large formal contexts efficiently, we propose a parallel algorithm for computing formal concepts, the aim of which is to make Close-by-One (CbO) and its variants highly parallelized and easy to apply. Current approaches to parallelization of CbO-type algorithms such as PCbO (Parallel CbO) compute concepts in the top L recursion levels in serial and then turn to parallel computation after that. To avoid massive serial computations and the hassle of choosing the hyperparameter L in real applications, our proposed algorithm enters parallelization at once after the computation of the top concept and its direct successors, and then uses a parallel reshuffle approach to rebalance the workload distribution among worker threads without communication with the main thread. We describe the algorithm and present an experimental evaluation of its performance and comparison with PCbO on various datasets. Empirical analyses demonstrate that our algorithm is superior when applied to various types of formal contexts.
Similar content being viewed by others
Availability of data and materials
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Andrews S (2011) In-close2, a high performance formal concept miner. In: Andrews S, Polovina S, Hill R, Akhgar B (eds) Conceptual structures for discovering knowledge. Springer, pp 50–62
Andrews S (2015) A ‘Best-of-Breed’ approach for designing a fast algorithm for computing fixpoints of Galois Connections. Inf Sci 295:633–649
Andrews S (2017) Making Use of Empty Intersections to Improve the Performance of CbO-Type Algorithms. In: Proceedings of the 14th international conference on formal concept analysis. Springer, pp 56–71
Andrews S (2018) A new method for inheriting canonicity test failures in Close-by-One type algorithms. In: Proceedings of the 14th international conference on concept lattices and their applications. Springer, pp 255–266
Andrews S, Orphanides C (2010) FcaBedrock, a Formal Context Creator. In: Croitoru M, Ferré S, Lukose D (eds) Conceptual structures: from information to intelligence. Springer, New York, pp 181–184
Belohlavek R, Outrata J, Trnecka M (2019) Factorizing Boolean matrices using formal concepts and iterative usage of essential entries. Inf Sci 489:37–49
Dong H, Ma Y, Gong X (2008) A new parallel algorithm for construction of concept lattice. J Front Comput Sci Technol 2(6):651–657
Dua D, Graff C (2017) UCI machine learning repository. http://archive.ics.uci.edu/ml. Accessed 21 June 2021
Ganter B (2010) Two basic algorithms in concept analysis. In: Kwuida L, Sertkaya B (eds) Formal concept analysis. Springer, New York, pp 312–340
Ganter B, Wille R (1999) Formal concept analysis: mathematical foundations. Springer, New York
Godin R, Missaoui R, Alaoui H (1995) Incremental concept formation algorithms based on Galois lattices. Comput Intell 11:246–267
Guo L, Jia Z, Li Q, Dai J (2021) Steadiness analysis of means-end conceptual paths and problem-chains based on concept lattices and similarity measuring. Int J Mach Learn Cyber. https://doi.org/10.1007/s13042-021-01309-5
Janostik R, Konecny J, Krajca P (2020) Interface between logical analysis of data and formal concept analysis. Eur J Oper Res 284:792–800
Li J, Mei C, Xu W, Qian Y (2015) Concept learning via granular computing: a cognitive viewpoint. Inf Sci 298:447–467
Kengue JFD, Valtchev P, Djamegni CT (2005) A parallel algorithm for lattice construction. In: Proceedings of the International conference on formal concept analysis. Springer, pp 249–264
Kodagoda N, Andrews S, Pulasinghe K (2017) A parallel version of the in-close algorithm. In: Proceedings of 6th national conference on technology and management, vol 7872818, pp 1–5
Kodagoda N, Pulasinghe K (2016) Comparision between features of CbO based algorithms for generating formal concepts. Int J Concept Struct Smart Appl 4:1–34
Konecny J, Krajca P (2021) Systematic categorization and evaluation of CbO-based algorithms in FCA. Inf Sci 575:265–288
Krajca P, Outrata J, Vychodil V (2010) Parallel algorithm for computing fixpoints of Galois connections. Ann Math Artif Intell 59:257–272
Krajca P, Outrata J, Vychodil V (2010) Advances in algorithms based on CbO. In: Proceedings of the 7th international conference on concept lattices and their applications, pp 325–337
Krajca P, Vychodil V (2009) Distributed algorithm for computing formal concepts using map-reduce framework. In: Adams NM, Robardet C, Siebes A, Boulicaut J-F (eds) Advances in intelligent data analysis VIII. Springer, New York, pp 333–344
Kuznetsov SO (1989) Interpretation on graphs and complexity characteristics of a search for specific patterns. Nauchno-Tekhnicheskaya Informatsiya, seriya 2 Informatsionnye protsessy i sistemy 23(1):23–27
Kuznetsov SO (1993) A fast algorithm for computing all intersections of objects in a finite semi-lattice. Nauchno-Tekhnicheskaya Informatsiya, seriya 2 Informatsionnye protsessy i sistemy 27(1):17–20
Kuznetsov SO (1996) Mathematical aspects of concept analysis. J Math Sci 80:1654–1698
Kuznetsov SO (1999) Learning of simple conceptual graphs from positive and negative examples. In: Żytkow JM, Rauch J (eds) Principles of data mining and knowledge discovery. Springer, Berlin, pp 384–391
Kuznetsov SO (2001) On computing the size of a lattice and related decision problems. Order 18:313–321
Kuznetsov SO, Obiedkov SA (2002) Comparing performance of algorithms for generating concept lattices. J Exp Theor Artif Intell 14:189–216
Kwon SE, Kim YT, Suh H, Lee H (2021) Identifying the mobile application repertoire based on weighted formal concept analysis. Expert Syst Appl 173:114678
Li J, Aswani Kumar C, Mei C, Wang X (2017) Comparison of reduction in formal decision contexts. Int J Approx Reason 80:100–122
Li X, Shao M-W, Zhao X-M (2017) Constructing lattice based on irreducible concepts. Int J Mach Learn Cyber 8:109–122
Ma J-M, Cai M-J, Zou C-J (2017) Concept acquisition approach of object-oriented concept lattices. Int J Mach Learn Cyber 8:123–134
Mi Y, Shi Y, Li J, Liu W, Yan M (2020) Fuzzy-based concept learning method: exploiting data with fuzzy conceptual clustering. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2020.2980794
Nourine L, Raynaud O (1999) A fast algorithm for building lattices. Inf Process Lett 71:199–204
Outrata J, Vychodil V (2012) Fast algorithm for computing fixpoints of Galois connections induced by object-attribute relational data. Inf Sci 185:114–127
Poelmans J, Kuznetsov SO, Ignatov DI, Dedene G (2013) Formal concept analysis in knowledge processing: a survey on models and techniques. Expert Syst Appl 40:6601–6623
Qian T, Wei L, Qi J (2017) Decomposition methods of formal contexts to construct concept lattices. Int J Mach Learn Cyber 8:95–108
Qin K, Lin H, Jiang Y (2020) Local attribute reductions of formal contexts. Int J Mach Learn Cyber 11:81–93
Shi Y, Mi Y, Li J, Liu W (2019) Concurrent concept-cognitive learning model for classification. Inf Sci 496:65–81
Strok F, Neznanov A (2010) Comparing and analyzing the computational complexity of FCA algorithms. In: Proceedings of the 2010 annual research conference of the South African institute of computer scientists and information technologists on. ACM Press, pp 417–420
Van der Merwe D, Obiedkov S, Kourie D (2004) AddIntent: a new incremental algorithm for constructing concept lattices. In: Lecture notes in artificial intelligence, pp 205–206
Wille R (1982) Restructuring lattice theory: an approach based on hierarchies of concepts. In: Rival I (ed) Ordered sets. Springer, New York, pp 445–470
Xu B, de Fréin R, Robson E, Foghlú Ó (2012) Distributed formal concept analysis algorithms based on an iterative MapReduce framework. In: Domenach F, Ignatov DI, Poelmans J (eds) Formal concept analysis. Springer, New York, pp 292–308
Zhang T, Bai D, Li H (2017) Parallel concept computing based on bottom-up decomposition of attribute topology. J Softw 28:3129–3145
Zhang T, Rong M, Shan H, Liu M (2021) Stability analysis of incremental concept tree for concept cognitive learning. Int J Mach Learn Cyber. https://doi.org/10.1007/s13042-021-01332-6
Zhao S, Pan G, Tao J, Luo Z, Li S, Wu Z (2020) Understanding smartphone users from installed app lists using boolean matrix factorization. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2020.2967644
Zou L, Zhang Z, Long J (2015) A fast incremental algorithm for constructing concept lattices. Expert Syst Appl 42:4474–4481
Acknowledgements
This research has been supported by the National Natural Science Foundation of China (No. 61976089), Natural Science Foundation of Hunan Province (2021JJ40361, 2021JJ30451) and the Hunan Provincial Science & Technology Project Foundation (2018TP1018, 2018RS3065).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zou, L., Chen, X., He, T. et al. Computing formal concepts in parallel via a workload rebalance approach. Int. J. Mach. Learn. & Cyber. 13, 2637–2648 (2022). https://doi.org/10.1007/s13042-022-01547-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01547-1