Abstract
This paper proposes a generic extension to propositional rule learners to handle multiple-instance data. In a multiple-instance representation, each learning example is represented by a bag” of fixed-length feature vectors”.Such a representation,lying somewhere between propositional and first-order representation, offers a tradeoff between the two. Naive-RipperMi is one implementation of this extension on the rule learning algorithm Ripper. Several pitfalls encountered by this naive extension during induction are explained. A new multiple-instance search bias based on decision tree techniques is then used to avoid these pitfalls. Experimental results show the benefits of this approach for solving propositionalized relational problems in terms of speed and accuracy.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Erick Alphonse and Celine Rouveirol. Lazy propositionalization for relational learning. In ECAI, 2000.
P. Auer, P. Long, and Ashwin Srinivasan. Approximating hyper-rectangles: Learning and pseudo-random sets. In Annual ACM Symposium on Theory of Computing, 1997.
Peter Auer. On learning from multi-instance examples: Empirical evaluation of a theoretical approach. In Proc. 14th International Conference on Machine Learning, 1997.
Hendrik Blockeel, Luc De Raedt, Nico Jacobs, and Bart Demoen. Scaling up inductive logic programming by learning from interpretations. Data Mining and Knowledge Discovery, 3(1):59–93, 1999.
Avrim Blum and Adam Kalai. A note on learning from multiple-instance examples. Machine Learning, 30, 1998.
Yann Chevaleyre and J.D. Zucker. Noise tolerant rule induction for multiple-instance data and potential data mining application. Tech. Rep. University of Paris 6, available at http://www-poleia.lip6.fr/~chevaley/michurning.ps, 2001.
William W. Cohen. Fast effective rule induction. In Proc. 12th International Conference on Machine Learning. Morgan Kaufmann, 1995.
Thomas G. Dietterich, Richard H. Lathrop, and Tomás Lozano-Pérez. Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence, 89(1–2), 1997.
Eibe Frank and Ian H.Witten. Generating accurate rule sets without global optimization. In Proc. 15th ICML, 1998.
Attilio Giordana, Lorenza Saitta, Michele Sebag, and Marco Botta. Analyzing relational learning in the phase transition framework. In Proc. 17th ICML, 2000.
J.U. Kietz. Some lower bounds for the computational complexity of inductive logic programming.In ECML, 1993.
Oded Maron and Aparna Lakshmi Ratan. Multiple-instance learning for natural scene classification.In Proc. 15th ICML, pages 341–349, 1998.
Luc De Raedt. Attribute-value learning versus inductive logic programming: The missing links. In Proc. 8th International Conference on ILP, 1998.
Michele Sebag and Celine Rouveirol. Tractable induction and classification in first order logic. In IJCAI, Nagoya, Japan, 1997.
A. Srinivasan and S. Muggleton. Comparing the use of background knowledge by two ilp systems. In L. de Raedt, editor, ILP-95., Katholieke Universiteit Leuven, 1995.
Jun Wang and Jean-Daniel Zucker. Solving multiple-instance problem: a lazy learning approach.In Proc. 17th ICML, 2000.
Jean-Daniel Zucker and Jean-Gabriel Ganascia. Learning structurally indeterminate clauses.In Proc. 8th International Conference on ILP. Springer-Verlag, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chevaleyre, Y., Zucker, JD. (2003). A Framework for Learning Rules from Multiple Instance Data. In: De Raedt, L., Flach, P. (eds) Machine Learning: ECML 2001. ECML 2001. Lecture Notes in Computer Science(), vol 2167. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44795-4_5
Download citation
DOI: https://doi.org/10.1007/3-540-44795-4_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42536-6
Online ISBN: 978-3-540-44795-5
eBook Packages: Springer Book Archive