Abstract
The multiple-instance model was motivated by the drug activity prediction problem where each example is a possible configuration for a molecule and each bag contains all likely configurations for the molecule. While there has been a significant amount of theoretical and empirical research directed towards this problem, most research performed under the multiple-instance model is for concept learning. However, binding affinity between molecules and receptors is quantitative and hence a real-valued classification is preferable.
In this paper we initiate a theoretical study of real-valued multiple instance learning. We prove that the problem of finding a target point consistent with a set of labeled multiple-instance examples (or bags) is NP-complete. We also prove that the problem of learning from realvalued multiple-instance examples is as hard as learning DNF. Another contribution of our work is in defining and studying a multiple-instance membership query (MI-MQ). We give a positive result on exactly learning the target point for a multiple-instance problem in which the learner is provided with a MI-MQ oracle and a single adversarially selected bag.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
R.A. Amar, D.R. Dooly, S.A. Goldman, and Q. Zhang. Multiple-Instance Learning of Real-Valued Data. In Proc. 18th International Conference on Machine Learning, pages 3–10. Morgan Kaufmann, 2001.
P. Auer, P. M. Long, and A. Srinivasan.Approximating hyper-rectangles: Learning and pseudo-random sets. In Proceedings of the Twenty-Ninth Annual ACM Symposium on Theory of Computing, pages 314–323. ACM, 1997.
P. Auer. On learning from multi-instance examples: Empirical evaluation of a theoretical approach. In Proc. 14th International Conference on Machine Learning, pages 21–29. Morgan Kaufmann, 1997.
R.S. Berry, S.A. Rice, and J. Ross. Physical Chemistry, Chapter 10 (Intermolecular Forces). John Wiley & Sons, 1980.
A. Blum and A. Kalai. A note on learning from multiple-instance examples. Machine Learning, 30:23–29, 1998.
T. G. Dietterich, R. H. Lathrop, and T. Lozano-Pérez. Solving the multipleinstance problem with axis-parallel rectangles. Artificial Intelligence, 89(1–2):31–71, 1997.
S.A. Goldman and S.D. Scott. Multiple-Instance Learning of Real-Valued Geometric Patterns. To appear in Annals of Mathematics and Artificial Intelligence.
M. Kearns. Efficient noise-tolerant learning from statistical queries. In Proc. 25th Annu. ACM Sympos. Theory Comput., pages 392–401. ACM Press, New York, NY, 1993.
P. M. Long and L. Tan. PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples. Machine Learning, 30:7–21, 1998. Earlier version in COLT96.
O. Maron. Learning from Ambiguity. PhD thesis, MIT, 1998. AI Technical Report 1639.
O. Maron and T. Lozano-Pérez. A framework for multiple-instance learning. Neural Information Processing Systems, 10, 1998.
O. Maron and A. Lakshmi Ratan. Multiple-instance learning for natural scene classification. In Proc. 15th International Conf. on Machine Learning, pages 341–349. Morgan Kaufmann, San Francisco, CA, 1998.
S. Ray and D. Page. Multiple instance regression. In Proc. 18th International Conference on Machine Learning, pages 425–432. Morgan Kaufmann, 2001.
G. Ruffo. Learning single and multiple instance decision trees for computer security applications. Doctoral dissertation. Department of Computer Science, University of Turin, Torino, Italy, 2000.
Wang and Zucker. Multiple-instance learning for natural scene classification. In Proc. 17th Int. Conf. on Machine Learning, pages 1119–1125. Morgan Kaufmann, San Francisco, CA, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dooly, D.R., Goldman, S.A., Kwek, S.S. (2001). Real-Valued Multiple-Instance Learning with Queries. In: Abe, N., Khardon, R., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2001. Lecture Notes in Computer Science(), vol 2225. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45583-3_14
Download citation
DOI: https://doi.org/10.1007/3-540-45583-3_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42875-6
Online ISBN: 978-3-540-45583-7
eBook Packages: Springer Book Archive