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

Kai Puolamaki; Emilia Oikarinen; Bo Kang; Jefrey Lijffijt; Tijl De Bie

doi:10.1109/ICDE.2018.00112

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

Kai Puolamaki, Emilia Oikarinen, Bo Kang, Jefrey Lijffijt, Tijl De Bie

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

4 Citations (Scopus)

Abstract

The 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.

Original language	English
Title of host publication	Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)
Publisher	IEEE
Pages	1212-1215
Number of pages	4
ISBN (Electronic)	9781538655207
DOIs	https://doi.org/10.1109/ICDE.2018.00112
Publication status	Published - 24 Oct 2018
MoE publication type	A4 Article in a conference publication
Event	International Conference on Data Engineering - Paris, France Duration: 16 Apr 2018 → 19 Apr 2018 Conference number: 34

Conference

Conference	International Conference on Data Engineering
Abbreviated title	ICDE
Country	France
City	Paris
Period	16/04/2018 → 19/04/2018

Keywords

Dimensionality reduction
Exploratory data analysis
Information theory
Subjective interestingness

Access to Document

10.1109/ICDE.2018.00112

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Interactive visual data exploration with subjective feedback: An information-theoretic approach'. Together they form a unique fingerprint.

Cite this

Puolamaki, 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) (pp. 1212-1215). [8509333] IEEE. https://doi.org/10.1109/ICDE.2018.00112

@inproceedings{49457aae02e34e58b2bb47843e52922b,

title = "Interactive visual data exploration with subjective feedback: An information-theoretic approach",

abstract = "The 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.",

keywords = "Dimensionality reduction, Exploratory data analysis, Information theory, Subjective interestingness",

author = "Kai Puolamaki and Emilia Oikarinen and Bo Kang and Jefrey Lijffijt and {De Bie}, Tijl",

note = "| openaire: EC/H2020/665501/EU//PEGASUS-2",

year = "2018",

month = "10",

day = "24",

doi = "10.1109/ICDE.2018.00112",

language = "English",

pages = "1212--1215",

booktitle = "Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)",

publisher = "IEEE",

address = "United States",

}

Puolamaki, 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.2018.00112

Interactive visual data exploration with subjective feedback : An information-theoretic approach. / Puolamaki, Kai; Oikarinen, Emilia; Kang, Bo; Lijffijt, Jefrey; De Bie, Tijl.

Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018). IEEE, 2018. p. 1212-1215 8509333.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Interactive visual data exploration with subjective feedback

T2 - An information-theoretic approach

AU - Puolamaki, Kai

AU - Oikarinen, Emilia

AU - Kang, Bo

AU - Lijffijt, Jefrey

AU - De Bie, Tijl

N1 - | openaire: EC/H2020/665501/EU//PEGASUS-2

PY - 2018/10/24

Y1 - 2018/10/24

N2 - The 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.

AB - The 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.

KW - Dimensionality reduction

KW - Exploratory data analysis

KW - Information theory

KW - Subjective interestingness

UR - http://www.scopus.com/inward/record.url?scp=85057121434&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2018.00112

DO - 10.1109/ICDE.2018.00112

M3 - Conference contribution

AN - SCOPUS:85057121434

SP - 1212

EP - 1215

BT - Proceedings of the 34th IEEE International Conference on Data Engineering (ICDE 2018)

PB - IEEE

ER -