Many datasets are -way fuzzy tensors, that is, -dimensional tables where every cell grades in the truth of a statement instantiated by the elements indexing the cell. In the special case where , fuzzy matrices encode to what extent objects (the rows) have attributes (the columns). Boolean tensors are another special case, in which the statement is always either false () or true (). Theoretically simple pattern-based models exist for -way Boolean or fuzzy tensors, and so do algorithms to discover sets of patterns well summarizing the tensors, according to these models. However, intuitively understanding such summaries has remained difficult. Tools specifically assisting data scientists in that endeavor are lacking. This article addresses that issue. It proposes the first interactive visualization for pattern-based summaries of fuzzy tensors. Pieces of information that are relevant to the interpretation of a summary are extracted from the study of the disjunctive box cluster model. They are turned into visual objects, attributes or interaction techniques. Special attention is given to allowing the exploration of summaries with many large patterns, as shown with the analysis of 55 patterns involving thousands of elements and summarizing a real-world tensor.
LeenenIVan MechelenIDe BoeckP, et al. INDCLAS: a three-way hierarchical classes model. Psychometrika1999; 64(1): 9–24.
2.
MiettinenP. Boolean tensor factorizations. In: IEEE international conference on data mining, Vancouver, BC, Canada, 11–14 December 2011, pp.447–456.
3.
BelohlavekRGlodeanuCVychodilV.Optimal factorization of three-way binary data using triadic concepts. Order2013; 30(2): 437–454.
4.
ErdősDMiettinenP. Walk ’n’ Merge: A scalable algorithm for Boolean tensor factorization. In: IEEE international conference on data mining, Dallas, TX, USA, 7–10 December 2013, pp.1037–1042.
5.
MetzlerSMiettinenP.Clustering Boolean tensors. Data Min Knowl Discov2015; 29(5): 1343–1373.
6.
RukatTHolmesCCYauC.Probabilistic Boolean tensor decomposition. In: international conference on machine learning, Stockholm, Sweden, 10–15 July 2018, pp.4410–4419.
7.
ParkNOhSKangU.Fast and scalable method for distributed Boolean tensor factorization. VLDB J2019; 28(4): 549–574.
8.
WanCChangWZhaoT, et al. Geometric all-way Boolean tensor decomposition. In: Annual conference on neural information processing systems, virtual, 6–12 December 2020, pp.2848–2857.
9.
MacielLAlvesJdos SantosVF, et al. Climbing the hill with ILP to grow patterns in fuzzy tensors. Int J Comput Intell Syst2020; 13(1): 1036–1047.
10.
RibeiroVHSCerfL. Summarizing fuzzy tensors with sub-tensors. In: ACM/SIGAPP symposium on applied computing, Tallinn, Estonia, 27–31 March 2023, pp.362–364.
11.
RibeiroVHSCerfL. Summarizing Boolean and fuzzy tensors with sub-tensors. Information Sciences2025; 719: 122489.
12.
BelohlavekRVychodilV. Factor analysis of incidence data via novel decomposition of matrices. In: International conference on formal concept analysis, Darmstadt, Germany, 21–24 May 2009, pp. 83–97.
13.
KaraevSMiettinenP.Algorithms for approximate subtropical matrix factorization. Data Min Knowl Discov2019; 33(2): 526–576.
14.
BelohlavekRTrneckovaM.Factorization of matrices with grades with overcovering. IEEE Trans Fuzzy Syst2024; 32(4): 1641–1652.
15.
MirkinBGKramarenkoAV. Approximate bicluster and tricluster boxes in the analysis of binary data. In: International conference on rough sets, fuzzy sets, data mining and granular computing, Moscow, Russia, 25–27 June 2011, pp.248–256.
16.
GrothausGAMuftiAMuraliTM.Automatic layout and visualization of biclusters. Algorithms Mol Biol2006; 1: 15.
17.
JinRXiangYFuhryD, et al. Overlapping matrix pattern visualization: a hypergraph approach. In: IEEE international conference on data mining, Pisa, Italy, 15–19 December 2008, pp.313–322.
18.
ColantonioADi PietroROcelloA, et al. Visual role mining: a picture is worth a thousand roles. IEEE Trans Knowl Data Eng2012; 24(6): 1120–1133.
19.
MaretteTMiettinenPNeumannS.Visualizing overlapping biclusterings and Boolean matrix factorizations. In: European conference on machine learning and knowledge discovery in databases, Turin, Italy, 18–22 September 2023, pp.743–758.
20.
TattiNMiettinenP.Boolean matrix factorization meets consecutive ones property. In: SIAM international conference on data mining, Calgary, AB, Canada, 2–4 May 2019, pp.729–737.
21.
SunMZhaoJWuH, et al. The effect of edge bundling and seriation on sensemaking of biclusters in bipartite graphs. IEEE Trans Vis Comput Graph2019; 25(10): 2983–2998.
22.
WuHVreekenJTattiN, et al. Uncovering the plot: detecting surprising coalitions of entities in multi-relational schemas. Data Min Knowl Discov2014; 28(5–6): 1398–1428.
23.
ZhaoJSunMChenF, et al. BiDots: visual exploration of weighted biclusters. IEEE Trans Vis Comput Graph2018; 24(1): 195–204.
24.
SunMShaikhARAlhooriH, et al. SightBi: exploring cross-view data relationships with biclusters. IEEE Trans Vis Comput Graph2022; 28(1): 54–64.
LehmannFWilleR. A triadic approach to formal concept analysis. In: International conference on conceptual structures, Santa Cruz, CA, USA, 14–18 August 1995, pp.32–43.
27.
KisLLSăcăreaCTroancăD.FCA tools bundle - a tool that enables dyadic and triadic conceptual navigation. In: International workshop “what can FCA do for artificial intelligence”?, The Hague, The Netherlands, 30 August 2016, pp.43–50.
28.
RudolphSSăcăreaCTroancăD. Towards a navigation paradigm for triadic concepts. In: International conference on formal concept analysis, Nerja, Spain, 23–26 June 2015, pp.252–267.
29.
GeorgiiETsudaKSchölkopfB.Multi-way set enumeration in weight tensors. Mach Learn2011; 82(2): 123–155.
30.
CerfLMeiraWJr. Complete discovery of high-quality patterns in large numerical tensors. In: IEEE international conference on data engineering, Chicago, IL, USA, 31 March–4 April, 2014, pp.448–459.
31.
KisLLSăcăreaCŞotropaDF.Visualizing conceptual structures using FCA tools bundle. In: International conference on conceptual structures, Edinburgh, UK, 20–22 June 2018, pp.193–196.
32.
RudolphSSăcăreaCTroancăD.Membership constraints in formal concept analysis. In: International joint conference on artificial intelligence, Buenos Aires, Argentina, 25–31 July 2015, pp.3186–3192.
33.
KruskalJB. Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis. Psychometrika1964; 29(1): 1–27.
