• Share
  • Email
  • Embed
  • Like
  • Save
  • Private Content
Non-Temporal Orderings for Extensional Concept Drift
 

Non-Temporal Orderings for Extensional Concept Drift

on

  • 221 views

 

Statistics

Views

Total Views
221
Views on SlideShare
202
Embed Views
19

Actions

Likes
0
Downloads
0
Comments
0

1 Embed 19

https://twitter.com 19

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    Non-Temporal Orderings for Extensional Concept Drift Non-Temporal Orderings for Extensional Concept Drift Presentation Transcript

    • Non-Temporal Orderings for Extensional Concept Drift Albert Mero˜o-Pe˜uela1,2 n n 1 Department 2 Data Stefan Schlobach1 of Computer Science, VU University Amsterdam, NL Archiving and Networked Services, KNAW, NL October 22th, 2013 First International Workshop on Semantic Statistics ISWC 2013 Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Motivation Stability of Meaning of Concepts As the world changes continuously, concepts also change their meaning over time. We call this concept drift We call this concept drift Smooth transitions Radical transitions (concept shift) Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Motivation Time-Based Stability of Meaning Concept drift takes place over time. Time is the intuitive ordering of the data. Dutch historical census data: 1795 1830 1840 1849 1859 1869 1879 1889 1899 1909 1919 1920 1930 1947 1956 1960 1971 Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Motivation Time-Based Stability of Meaning Concept drift takes place over time. Time is the intuitive ordering of the data. Dutch historical census data: 1795 1830 1840 1849 1859 1869 1879 1889 1899 1909 1919 1920 1930 1947 1956 1960 1971 But no time series in the challenge data! Australia: 2011 France: 2010 Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Motivation No-Time Based Stability of Meaning 1 Resignation 2 Discard time for this experiment No time, no party? Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Motivation No-Time Based Stability of Meaning Consider time as just one of all possible dimensions that can be used as data orderings. Meaningful orderings (i.e. intrinsically dynamic): GDP per capita Stock markets Population density (Il)literacy Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Case-Study Experiment Setup Can we detect drastic extensional drifts over orderings other than time? E.g. Is there drift in the concept of youth unemployment1 in Australia/France as a selected ordering grows? Australia: GDP per capita per state France: Population density per departement 1 15-24 years old considered standard Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Case-Study Querying SPARQL template for unfolding RDF Data Cubes Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Case-Study Querying Data sources: local endpoint, DBPedia (for the orderings) Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Case-Study Querying Age range 15-19 years Gender Male Age range 15 to 19 years Location New South Wales Gender Women Location Tarn Mero˜o-Pe˜uela, A. et al. n n Occupation Unemployed, Total Occupation Unemployed Population 17456 Population 1.345e03 Extensional Concept Drift GDP 57828 Density 64.17
    • Case-Study 1.0 0.8 0.6 0.0 0.0 0.2 0.4 p.density.yu 0.6 0.4 0.2 p.gdp 0.8 1.0 Results 1 2 3 4 5 6 7 8 Index 0 20 40 60 80 Index Drift of youth unemployment in Australian states using GDP per capita as ordering Mero˜o-Pe˜uela, A. et al. n n Drift of youth unemployment in French departements using population density as ordering Extensional Concept Drift
    • Case-Study p.density.dist 0.95 0.96 0.97 0.98 0.99 1.00 −1 −2 −4 −3 p.gdp.dist 0 1 Results 2 4 6 8 Index 0 20 40 60 80 Index Drift of youth unemployment in Australian states using GDP per capita as ordering (smooth function) Mero˜o-Pe˜uela, A. et al. n n Drift of youth unemployment in French departements using population density as ordering (smooth function) Extensional Concept Drift
    • Conclusions Concept drift: concepts change over time No time, but party Meaningful orderings as valuable as time to study concept drift (smooth transition assumption) Takes full advantage of Semantic Web data Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift
    • Thank you Questions, suggestions? @albertmeronyo http://www.cedar-project.nl http://www.data2semantics.org Mero˜o-Pe˜uela, A. et al. n n Extensional Concept Drift