Advertisement

Applied Intelligence

, Volume 31, Issue 1, pp 47–68 | Cite as

Multi-instance clustering with applications to multi-instance prediction

  • Min-Ling Zhang
  • Zhi-Hua Zhou
Article

Abstract

In the setting of multi-instance learning, each object is represented by a bag composed of multiple instances instead of by a single instance in a traditional learning setting. Previous works in this area only concern multi-instance prediction problems where each bag is associated with a binary (classification) or real-valued (regression) label. However, unsupervised multi-instance learning where bags are without labels has not been studied. In this paper, the problem of unsupervised multi-instance learning is addressed where a multi-instance clustering algorithm named Bamic is proposed. Briefly, by regarding bags as atomic data items and using some form of distance metric to measure distances between bags, Bamic adapts the popular k -Medoids algorithm to partition the unlabeled training bags into k disjoint groups of bags. Furthermore, based on the clustering results, a novel multi-instance prediction algorithm named Bartmip is developed. Firstly, each bag is re-represented by a k-dimensional feature vector, where the value of the i-th feature is set to be the distance between the bag and the medoid of the i-th group. After that, bags are transformed into feature vectors so that common supervised learners are used to learn from the transformed feature vectors each associated with the original bag’s label. Extensive experiments show that Bamic could effectively discover the underlying structure of the data set and Bartmip works quite well on various kinds of multi-instance prediction problems.

Keywords

Machine learning Multi-instance learning Clustering Representation transformation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Dietterich TG, Lathrop RH, Lozano-Pérez T (1997) Solving the multiple-instance problem with axis-parallel rectangles. Artif Intell 39(1-2):31–71 CrossRefGoogle Scholar
  2. 2.
    Weidmann N, Frank E, Pfahringer B (2003) A two-level learning method for generalized multi-instance problem. In: Lavrač N, Gamberger D, Blockeel H, Todorovski L (eds) Lecture notes in artificial intelligence, vol 2837. Springer, Berlin, pp 468–579 Google Scholar
  3. 3.
    Scott S, Zhang J, Brown J (2003) On generalized multiple-instance learning. Technical report UNL-CSE-2003-5, Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE Google Scholar
  4. 4.
    Amar RA, Dooly DR, Goldman SA, Zhang Q (2001) Multiple-instance learning of real-valued data. In: Proceedings of the 18th international conference on machine learning, Williamstown, MA, 2001, pp 3–10 Google Scholar
  5. 5.
    Ray S, Page D (2001) Multiple instance regression. In: Proceedings of the 18th international conference on machine learning, Williamstown, MA, 2001, pp 425–432 Google Scholar
  6. 6.
    Dooly DR, Zhang Q, Goldman SA, Amar RA (2002) Multiple-instance learning of real-valued data. J Mach Learn Res 3:651–678 CrossRefGoogle Scholar
  7. 7.
    Han J, Kamber M (2001) Data mining: concepts and techniques. Morgan Kaufmann, San Francisco Google Scholar
  8. 8.
    Edgar GA (1995) Measure, Topology, and Fractal Geometry, 3rd edn. Springer, Berlin Google Scholar
  9. 9.
    Long PM, Tan L (1998) Pac learning axis-aligned rectangles with respect to product distribution from multiple-instance examples. Mach Learn 20(1):7–21 CrossRefGoogle Scholar
  10. 10.
    Auer P, Long PM, Srinivasan A (1998) Approximating hyper-rectangles: learning and pseudo-random sets. J Comput Syst Sci 57(3):376–388 MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Auer P (1997) On learning from multi-instance examples: empirical evaluation of a theoretical approach. In: Proceedings of the 14th international conference on machine learning, Nashville, TN, 1997, pp 21–29 Google Scholar
  12. 12.
    Blum A, Kalai A (1998) A note on learning from multiple-instance examples. Mach Learn 30(1):23–29 MATHCrossRefGoogle Scholar
  13. 13.
    Goldman SA, Kwek SS, Scott SD (2001) Agnostic learning of geometric patterns. J Comput Syst Sci 62(1):123–151 MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Goldman SA, Scott SD (2003) Multiple-instance learning of real-valued geometric patterns. Ann Math Artif Intell 39(3):259–290 MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Maron O, Lozano-Pérez T (1998) A framework for multiple-instance learning. In: Jordan MI, Kearns MJ, Solla SA (eds) Advances in neural information processing systems, vol 10. MIT Press, Cambridge, pp 570–576 Google Scholar
  16. 16.
    Zhang Q, Goldman SA (2002) Em-dd: an improved multiple-instance learning technique. In: Dietterich TG, Becker S, Ghahramani Z (eds) Advances in neural information processing systems, vol 14. MIT Press, Cambridge, pp 1073–1080 Google Scholar
  17. 17.
    Chen Y, Wang JZ (2004) Image categorization by learning and reasoning with regions. J Mach Learn Res 5:913–939 Google Scholar
  18. 18.
    Wang J, Zucker J-D (2000) Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the 17th international conference on machine learning, San Francisco, CA, 2000, pp 1119–1125 Google Scholar
  19. 19.
    Ruffo G (2000) Learning single and multiple decision trees for security applications. Ph.D. thesis, Department of Computer Science, University of Turin, Italy, 2000 Google Scholar
  20. 20.
    Chevaleyre Y, Zucker J-D (2001) Solving multiple-instance and multiple-part learning problems with decision trees and decision rules. Application to the mutagenesis problem. In: Stroulia E, Matwin S (eds) Lecture notes in artificial intelligence, vol 2056. Springer, Berlin, pp 204–214 Google Scholar
  21. 21.
    Blockeel H, Page D, Srinivasan A (2005) Multi-instance tree learning. In: Proceedings of the 22nd international conference on machine learning, Bonn, Germany, 2005, pp 57–64 Google Scholar
  22. 22.
    Xu X, Frank E (2004) Logistic regression and boosting for labeled bags of instances. In: Dai H, Srikant R, Zhang C-Q (eds) Lecture notes in computer science, vol 3056. Springer, Berlin, pp 272–281 Google Scholar
  23. 23.
    Ramon J, De Raedt L (2000) Multi instance neural networks. In: Proceedings of ICML-2000, workshop on attribute-value and relational learning, San Francisco, CA, 2000 Google Scholar
  24. 24.
    Zhou Z-H, Zhang M-L (2002) Neural networks for multi-instance learning. Technical report, AI Lab, Computer Science and Technology Department, Nanjing University, Nanjing, China Google Scholar
  25. 25.
    Zhang M-L, Zhou Z-H (2004) Improve multi-instance neural networks through feature selection. Neural Process Lett 19(1):1–10 MATHCrossRefGoogle Scholar
  26. 26.
    Bouchachia A (2004) Multiple instance learning with radial basis function neural networks. In: Pal NR, Kasabov N, Mudi RK (eds) Lecture notes in computer science, vol 3316. Springer, Berlin, pp 440–445 Google Scholar
  27. 27.
    Zhang M-L, Zhou Z-H (2006) Adapting RBF neural networks to multi-instance learning. Neural Process Lett 23(1):1–26 CrossRefGoogle Scholar
  28. 28.
    Gärtner T, Flach PA, Kowalczyk A, Smola AJ (2002) Multi-instance kernels. In: Proceedings of the 19th international conference on machine learning, Sydney, Australia, 2002, pp 179–186 Google Scholar
  29. 29.
    Andrews S, Tsochantaridis I, Hofmann T (2003) Support vector machines for multiple-instance learning. In: Becker S, Thrun S, Obermayer K (eds) Advances in neural information processing systems, vol 15. MIT Press, Cambridge, pp 561–568 Google Scholar
  30. 30.
    Cheung P-M, Kwok JT (2006) A regularization framework for multiple-instance learning. In: Proceedings of the 23th international conference on machine learning, Pittsburgh, PE, 2006, pp 193–200 Google Scholar
  31. 31.
    Zhou Z-H, Zhang M-L (2003) Ensembles of multi-instance learners. In: Lavrač N, Gamberger D, Blockeel H, Todorovski L (eds) Lecture notes in artificial intelligence, vol 2837. Springer, Berlin, pp 492–502 Google Scholar
  32. 32.
    Andrews S, Hofmann T (2004) Multiple-instance learning via disjunctive programming boosting. In: Thrun S, Saul LK, Schölkopf B (eds) Advances in neural information processing systems, vol 16. MIT Press, Cambridge Google Scholar
  33. 33.
    Auer P, Ortner R (2004) A boosting approach to multiple instance learning. In: Boulicaut J-F, Esposito F, Giannotti F, Pedreschi D (eds) Lecture notes in artificial intelligence, vol 3201. Springer, Berlin, pp 63–74 Google Scholar
  34. 34.
    Viola P, Platt J, Zhang C (2006) Multiple instance boosting for object detection. In: Weiss Y, Schölkopf B, Platt J (eds) Advances in neural information processing systems, vol 18. MIT Press, Cambridge, pp 1419–1426 Google Scholar
  35. 35.
    Huang X, Chen S-C, Shyu M-L, Zhang C (2002) Mining high-level user concepts with multiple instance learning and relevance feedback for content-based image retrieval. In: Zaïane OR, Simoff SJ, Djeraba C (eds) Lecture notes in artificial intelligence, vol 2797. Springer, Berlin, pp 50–67 Google Scholar
  36. 36.
    Yang C, Lozano-Pérez T (2000) Image database retrieval with multiple-instance learning techniques. In: Proceedings of the 16th international conference on data engineering, San Diego, CA, 2000, pp 233–243 Google Scholar
  37. 37.
    Zhang Q, Yu W, Goldman SA, Fritts JE (2002) Content-based image retrieval using multiple-instance learning. In: Proceedings of the 19th international conference on machine learning, Sydney, Australia, 2002, pp 682–689 Google Scholar
  38. 38.
    Zhou Z-H, Zhang M-L, Chen K-J (2003) A novel bag generator for image database retrieval with multi-instance learning techniques. In: Proceedings of the 15th IEEE international conference on tools with artificial intelligence, Sacramento, CA, 2003, pp 565–569 Google Scholar
  39. 39.
    Rahmani R, Goldman SA (2006) Missl: multiple-instance semi-supervised learning. In: Proceedings of the 23rd international conference on machine learning, Pittsburgh, PE, 2006, pp 705–712 Google Scholar
  40. 40.
    Maron O, Ratan AL (1998) Multiple-instance learning for natural scene classification. In: Proceedings of the 15th international conference on machine learning, Madison, WI, 1998, pp 341–349 Google Scholar
  41. 41.
    McGovern A, Barto AG (2001) Automatic discovery of subgoals in reinforcement learning using diverse density. In: Proceedings of the 18th international conference on machine learning, Williamstown, MA, 2001, pp 361–368 Google Scholar
  42. 42.
    Zhou Z-H, Jiang K, Li M (2005) Multi-instance learning based web mining. Appl Intell 22(2):135–147 CrossRefGoogle Scholar
  43. 43.
    Zhou Z-H, Zhang M-L (2007) Solving multi-instance problems with classifier ensemble based on constructive clustering. Knowl Inf Syst 11(2):155–170 CrossRefGoogle Scholar
  44. 44.
    Tao Q, Scott S (2004) A faster algorithm for generalized multiple-instance learning. In: Proceedings of the 17th international Florida artificial intelligence research society conference, Miami Beach, FL, 2004, pp 550–555 Google Scholar
  45. 45.
    Tao Q, Scott S, Vinodchandran NV, Osugi TT (2004) Svm-based generalized multiple-instance learning via approximate box counting. In: Proceedings of the 21st international conference on machine learning, Banff, Canada, 2004, pp 799–806 Google Scholar
  46. 46.
    Tao Q, Scott S, Vinodchandran NV, Osugi TT, Mueller B (2004) An extended kernel for generalized multiple-instance learning. In: Proceedings of the 16th IEEE international conference on tools with artificial intelligence, Boca Raton, FL, 2004, pp 272–277 Google Scholar
  47. 47.
    De Raedt L (1998) Attribute-value learning versus inductive logic programming: the missing links. In: Page D (ed) Lecture notes in artificial intelligence, vol 1446. Springer, Berlin, pp 1–8 Google Scholar
  48. 48.
    Alphonse É, Matwin S (2004) Filtering multi-instance problems to reduce dimensionality in relational learning. J Intell Inf Syst 22(1):23–40 CrossRefGoogle Scholar
  49. 49.
    McGovern A, Jensen D (2003) Identifying predictive structures in relational data using multiple instance learning. In: Proceedings of the 20th international conference on machine learning, Washington, DC, 2003, pp 528–535 Google Scholar
  50. 50.
    Günter S, Bunke H (2003) Validation indices for graph clustering. Pattern Recogn Lett 24(8):1107–1113 MATHCrossRefGoogle Scholar
  51. 51.
    Quinlan JR (1993) C4.5: Programs for machine learning. Morgan Kaufmann, San Mateo Google Scholar
  52. 52.
    Blake C, Keogh E, Merz CJ (1998) UCI repository of machine learning databases [http://www.ics.uci.edu/~mlearn/mlrepository.html]. Technical report, Department of Information and Computer Science, University of California, Irvine, CA
  53. 53.
    Berry RS, Rice SA, Ross J (1980) Physical Chemistry. Wiley, New York, Chapter 10, Intermolecular Forces Google Scholar
  54. 54.
    Liu H, Motoda H (1998) Feature selection for knowledge discovery and data mining. Kluwer Academic, Norwell MATHGoogle Scholar
  55. 55.
    Wang C, Scott SD, Zhang J, Tao Q, Fomenko D, Gladyshev V (2004) A study in modeling low-conservation protein superfamilies. Technical report UNL-CSE-2004-0003, Department of Computer Science and Engineering, University of Nebraska, Lincoln, NE Google Scholar
  56. 56.
    Kim J, Moriyama EN, Warr CG, Clyne PJ, Carlson JR (2000) Identification of novel multi-transmembrane proteins from genomic databases using quasi-periodic structural properties. Bioinform 16(9):767–775 CrossRefGoogle Scholar
  57. 57.
    Littlestone N (1991) Redundant noisy attributes, attribute errors, and linear threshold learning using winnow. In: Proceedings of the 4th annual workshop on computational learning theory, Santa Cruz, CA, 1991, pp 147–156 Google Scholar
  58. 58.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York Google Scholar
  59. 59.
    Dietterich TG (2000) Ensemble methods in machine learning. In: Kittler J, Roli F (eds) Lecture notes in computer science, vol 1867. Springer, Berlin, pp 1–15 Google Scholar
  60. 60.
    Chang C-C, Lin C-J (2001) Libsvm: a library for support vector machines. Technical report, Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan Google Scholar
  61. 61.
    Ray S, Craven M (2005) Supervised versus multiple instance learning: an empirical comparison. In: Proceedings of the 22nd international conference on machine learning, Bonn, Germany, 2005, pp 697–704 Google Scholar
  62. 62.
    Tan X, Chen S, Zhou Z-H, Liu J (2006) Learning non-metric partial similarity based on maximal margin criterion. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, New York, NY, 2006, pp 138–145 Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.National Key Laboratory for Novel Software TechnologyNanjing UniversityNanjingChina
  2. 2.College of Computer and Information EngineeringHohai UniversityNanjingChina

Personalised recommendations