Interactive visual data exploration with subjective feedback: An information-theoretic approach

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorPuolamaki, Kaien_US
dc.contributor.authorOikarinen, Emiliaen_US
dc.contributor.authorKang, Boen_US
dc.contributor.authorLijffijt, Jefreyen_US
dc.contributor.authorDe Bie, Tijlen_US
dc.contributor.departmentDepartment of Computer Scienceen
dc.contributor.groupauthorProfessorship Kaski Samuelen
dc.contributor.organizationGhent Universityen_US
dc.date.accessioned2018-12-21T10:30:15Z
dc.date.available2018-12-21T10:30:15Z
dc.date.issued2018-10-24en_US
dc.description| openaire: EC/H2020/665501/EU//PEGASUS-2
dc.description.abstractThe exploration of high-dimensional real-valued data is one of the fundamental exploratory data analysis (EDA) tasks. Existing methods use predefined criteria for the representation of data. There is a lack of methods eliciting the user's knowledge from the data and showing patterns the user does not know yet. We provide a theoretical model where the user can input the patterns she has learned as knowledge. The background knowledge is used to find a MaxEnt distribution of the data, and the user is shown maximally informative projections in which the MaxEnt distribution and the data differ the most. We provide an interactive open source EDA system, study its performance, and present use cases on real data.en
dc.description.versionPeer revieweden
dc.format.extent4
dc.identifier.citationPuolamaki, K, Oikarinen, E, Kang, B, Lijffijt, J & De Bie, T 2018, Interactive visual data exploration with subjective feedback : An information-theoretic approach. in Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)., 8509333, IEEE, pp. 1212-1215, International Conference on Data Engineering, Paris, France, 16/04/2018. https://doi.org/10.1109/ICDE.2018.00112en
dc.identifier.doi10.1109/ICDE.2018.00112en_US
dc.identifier.isbn9781538655207
dc.identifier.otherPURE UUID: 49457aae-02e3-4e58-b2bb-47843e52922ben_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/49457aae-02e3-4e58-b2bb-47843e52922ben_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/35650
dc.identifier.urnURN:NBN:fi:aalto-201812216659
dc.language.isoenen
dc.relationinfo:eu-repo/grantAgreement/EC/H2020/665501/EU//PEGASUS-2en_US
dc.relation.fundinginforeal-valued data and the background distribution modeled by multivariate Gaussian distributions. The ideas could be generalized to other data types (e.g., categorical or ordinal data), or to higher-order statistics, likely in a straightforward manner, as the mathematics of exponential family distribution would lead to similar derivations. For concrete applications for our approach and the SIDER tool there is potential in, e.g., computational flow cytometry. Initial experiments with samples up to tens of thousands rows from flow-cytometry data [9] has shown the computations in SIDER to scale up well and the projections to reveal structure in the data potentially interesting to the application specialist. Acknowledgements. This work has been supported by the ERC under the EU’s Seventh Framework Programme (FP/2007-2013) / ERC Grant Agreement no. 615517, the FWO (project no. G091017N, G0F9816N), the EU’s Horizon 2020 research and innovation programme and the FWO under the MSC Grant Agreement no. 665501, the Academy of Finland (288814, 313513), and Tekes (Revolution of Knowledge Work project).
dc.relation.ispartofInternational Conference on Data Engineeringen
dc.relation.ispartofseriesProceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)en
dc.relation.ispartofseriespp. 1212-1215en
dc.rightsrestrictedAccessen
dc.subject.keywordDimensionality reductionen_US
dc.subject.keywordExploratory data analysisen_US
dc.subject.keywordInformation theoryen_US
dc.subject.keywordSubjective interestingnessen_US
dc.titleInteractive visual data exploration with subjective feedback: An information-theoretic approachen
dc.typeA4 Artikkeli konferenssijulkaisussafi

Files

Collections

[article-cris] Perustieteiden korkeakoulu / SCI