Solving Multiple-Instance and Multiple-Part Learning Problems with Decision Trees and Rule Sets. Application to the Mutagenesis Problem
In recent work, Dietterich et al. (1997) have presented the problem of supervised multiple-instance learning and how to solve it by building axis-parallel rectangles. This problem is encountered in contexts where an object may have different possible alternative configurations, each of which is described by a vector. This paper introduces the multiple-part problem, which is related to the multiple-instance problem, and shows how it can be solved using the multiple-instance algorithms. These two so-called “multiple“ problems could play a key role both in the development of efficient algorithms for learning the relations between the activity of a structured object and its structural properties and in relational learning. This paper analyzes and tries to clarify multiple-problem solving. It goes on to propose multiple-instance extensions of classical learning algorithms to solve multiple-problems by learning multiple-decision trees (Id3-Mi) and multiple-decision rules (Ripper- Mi). In particular, it suggests a new multiple-instance entropy function and a multiple-instance coverage function. Finally, it successfully applies the multiple-part framework on the well-known mutagenesis prediction problem.
KeywordsInductive Logic Programming Linearity Hypothesis Multiple Instance Learning Learn Decision Tree Inductive Logic Programming System
Unable to display preview. Download preview PDF.
- 1.Alphonse, E., Rouveirol, C. 1999. Selective Propositionalization for Relational Learning. Principles and Practice of Knowledge Discovery in Databases.Google Scholar
- 2.Auer, P. 1997. On learning from multi-instances examples. Empirical evaluation of a theoretical approach. 14th International Conference on Machine Learning.Google Scholar
- 3.Blum, A. and A. Kalai 1997. A note on learning from multiple-instances examples. Machine Learning.Google Scholar
- 4.Cohen, W. 1995. Fast Effective Rule Induction. International Conference on Machine Learning.Google Scholar
- 5..Dietterich, T. 1990. Inductive Learning from Preclassified Training Examples. Readings in Machine Learning: 45–56.Google Scholar
- 7.Giordana, A. and L. Saitta 1990. Abstraction: a general framework for learning. AAAI Workshop on Automated Generation of Approximations and Abstraction.Google Scholar
- 9.Maron, O. and T. Lozano-PŽrez. 1998. A Framework for Multiple-Instance Learning. Neural Information Processing SystemsGoogle Scholar
- 10.Quinlan, J.-R. 1986. Induction of Decision Trees. Machine Learning(1): 81–106.Google Scholar
- 11.Zucker, J.-D. and J.-G. Ganascia 1996. Changes of Representation for Efficient Learning in Structural Domains. International Conf. in Machine Learning.Google Scholar
- 12.Zucker, J.-D., J.-G. Ganascia, Bournaud I. 1998. Relational Knowledge Discovery in a Chinese Characters Database.Applied Artificial Intelligence Journal, Special Issue on KDD in Structural Domains.Google Scholar