nips nips2007 nips2007-136 nips2007-136-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Burr Settles, Mark Craven, Soumya Ray
Abstract: We present a framework for active learning in the multiple-instance (MI) setting. In an MI learning problem, instances are naturally organized into bags and it is the bags, instead of individual instances, that are labeled for training. MI learners assume that every instance in a bag labeled negative is actually negative, whereas at least one instance in a bag labeled positive is actually positive. We consider the particular case in which an MI learner is allowed to selectively query unlabeled instances from positive bags. This approach is well motivated in domains in which it is inexpensive to acquire bag labels and possible, but expensive, to acquire instance labels. We describe a method for learning from labels at mixed levels of granularity, and introduce two active query selection strategies motivated by the MI setting. Our experiments show that learning from instance labels can significantly improve performance of a basic MI learning algorithm in two multiple-instance domains: content-based image retrieval and text classification. 1
[1] S. Andrews, I. Tsochantaridis, and T. Hofmann. Support vector machines for multiple-instance learning. In Advances in Neural Information Processing Systems (NIPS), pages 561–568. MIT Press, 2003.
[2] D. Cohn, L. Atlas, and R. Ladner. Improving generalization with active learning. Machine Learning, 15(2):201–221, 1994.
[3] T. Dietterich, R. Lathrop, and T. Lozano-Perez. Solving the multiple-instance problem with axis-parallel rectangles. Artificial Intelligence, 89:31–71, 1997.
[4] J.T. Eppig, C.J. Bult, J.A. Kadin, J.E. Richardson, J.A. Blake, and the members of the Mouse Genome Database Group. The Mouse Genome Database (MGD): from genes to mice–a community resource for mouse biology. Nucleic Acids Research, 33:D471–D475, 2005. http://www.informatics.jax.org.
[5] D. Lewis and J. Catlett. Heterogeneous uncertainty sampling for supervised learning. In Proceedings of the International Conference on Machine Learning (ICML), pages 148–156. Morgan Kaufmann, 1994.
[6] O. Maron and T. Lozano-Perez. A framework for multiple-instance learning. In Advances in Neural Information Processing Systems (NIPS), pages 570–576. MIT Press, 1998.
[7] J. Nocedal and S.J. Wright. Numerical Optimization. Springer, 1999.
[8] R. Rahmani and S.A. Goldman. MISSL: Multiple-instance semi-supervised learning. In Proceedings of the International Conference on Machine Learning (ICML), pages 705–712. ACM Press, 2006.
[9] S. Ray and M. Craven. Supervised versus multiple instance learning: An empirical comparison. In Proceedings of the International Conference on Machine Learning (ICML), pages 697–704. ACM Press, 2005.
[10] Q. Tao, S.D. Scott, and N.V. Vinodchandran. SVM-based generalized multiple-instance learning via approximate box counting. In Proceedings of the International Conference on Machine Learning (ICML), pages 779–806. Morgan Kaufmann, 2004.
[11] X. Zhu, J. Lafferty, and Z. Ghahramani. Combining active learning and semi-supervised learning using gaussian fields and harmonic functions. In Proceedings of the ICML Workshop on the Continuum from Labeled to Unlabeled Data, pages 58–65, 2003.