Abstract
Taxonomies for a set of features occur in many real-world domains. An example is provided by paleontology, where the task is to determine the age of a fossil site on the basis of the taxa that have been found in it. As the fossil record is very noisy and there are lots of gaps in it, the challenge is to consider taxa at a suitable level of aggregation: species, genus, family, etc. For example, some species can be very suitable as features for the age prediction task, while for other parts of the taxonomy it would be better to use genus level or even higher levels of the hierarchy. A default choice is to select a fixed level (typically species or genus); this misses the potential gain of choosing the proper level for sets of species separately. Motivated by this application we study the problem of selecting an antichain from a taxonomy that covers all leaves and helps to predict better a specified target variable. Our experiments on paleontological data show that choosing antichains leads to better predictions than fixing specific levels of the taxonomy beforehand.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network flows: theory, algorithms, and applications. Prentice-Hall, Inc., Englewood Cliffs (1993)
Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. Artif. Intell. 97(1-2), 245–271 (1997)
Cai, L., Hofmann, T.: Exploiting known taxonomies in learning overlapping concepts. In: IJCAI 2007, pp. 714–719 (2007)
Charikar, M., Guruswami, V., Kumar, R., Rajagopalan, S., Sahai, A.: Combinatorial feature selection problems. In: FOCS 2000, page 631 (2000)
desJardins, M., Getoor, L., Koller, D.: Using feature hierarchies in Bayesian network learning. In: Choueiry, B.Y., Walsh, T. (eds.) SARA 2000. LNCS (LNAI), vol. 1864, pp. 260–270. Springer, Heidelberg (2000)
Ford, L.R., Fulkerson, D.R.: Maximal flow through a network. Canadian Journal of Mathematics 8, 399–404 (1956)
Fortelius, M., Gionis, A., Jernvall, J., Mannila, H.: Spectral ordering and biochronology of european fossil mammals. Paleobiology 32, 206–214 (2006)
Fortelius, M.: Neogene of the old world database of fossil mammals (NOW) (2008), http://www.helsinki.fi/science/now/
Jernvall, J., Fortelius, M.: Common mammals drive the evolutionary increase of hypsodonty in the neogene. Nature 417, 538–540 (2002)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artif. Intell. 97(1-2), 273–324 (1997)
Lavrač, N., Gamberger, D.: Relevancy in constraint-based subgroup discovery. In: Constraint-Based Mining and Inductive Databases, pp. 243–266 (2004)
Liow, L.H., Fortelius, M., Bingham, E., Lintulaakso, K., Mannila, H., Flynn, L., Stenseth, N.C.: Stenseth higher origination and extinction rates in larger mammals. PNAS 105, 6097–6102 (2008)
Srikant, R., Agrawal, R.: Mining generalized association rules. Future Gener. Comput. Syst. 13(2-3), 161–180 (1997)
Yun, C., Chuang, K., Chen, M.: Using category-based adherence to cluster market-basket data. In: ICDM 2002, p. 546 (2002)
Zhang, J., Kang, D.-K., Silvescu, A., Honavar, V.: Learning accurate and concise naïve bayes classifiers from attribute value taxonomies and data. Knowl. Inf. Syst. 9(2), 157–179 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Berlin Heidelberg
About this paper
Cite this paper
Garriga, G.C., Ukkonen, A., Mannila, H. (2008). Feature Selection in Taxonomies with Applications to Paleontology. In: Jean-Fran, JF., Berthold, M.R., Horváth, T. (eds) Discovery Science. DS 2008. Lecture Notes in Computer Science(), vol 5255. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88411-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-88411-8_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88410-1
Online ISBN: 978-3-540-88411-8
eBook Packages: Computer ScienceComputer Science (R0)