Advanced search
1 file | 207.22 KB
Author
Organization
Abstract
The F-measure, originally introduced in information retrieval, is nowadays routinely used as a performance metric for problems such as binary classification, multi-label classification, and structured output prediction. Optimizing this measure remains a statistically and computationally challenging problem, since no closed-form maximizer exists. Current algorithms are approximate and typically rely on additional assumptions regarding the statistical distribution of the binary response variables. In this paper, we present an algorithm which is not only computationally efficient but also exact, regardless of the underlying distribution. The algorithm requires only a quadratic number of parameters of the joint distribution (with respect to the number of binary responses). We illustrate its practical performance by means of experimental results for multi-label classification.

Downloads

  • Dembczynski 2011 NIPS 0815.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 207.22 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Dembczyński, Krzysztof, Willem Waegeman, Weiwei Cheng, and Eyke Hüllermeier. 2011. “An Exact Algorithm for F-measure Maximization.” In Advances in Neural Information Processing Systems, ed. J Shawe-Taylor, RS Zemel, P Bartlett, F Pereira, and KQ Weinberger. Vol. 24. Neural Information Processing Systems Foundation.
APA
Dembczyński, Krzysztof, Waegeman, W., Cheng, W., & Hüllermeier, E. (2011). An exact algorithm for F-measure maximization. In J Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems (Vol. 24). Presented at the 2011 Neural Information Processing Systems (NIPS 2011), Neural Information Processing Systems Foundation.
Vancouver
1.
Dembczyński K, Waegeman W, Cheng W, Hüllermeier E. An exact algorithm for F-measure maximization. In: Shawe-Taylor J, Zemel R, Bartlett P, Pereira F, Weinberger K, editors. Advances in Neural Information Processing Systems. Neural Information Processing Systems Foundation; 2011.
MLA
Dembczyński, Krzysztof, Willem Waegeman, Weiwei Cheng, et al. “An Exact Algorithm for F-measure Maximization.” Advances in Neural Information Processing Systems. Ed. J Shawe-Taylor et al. Vol. 24. Neural Information Processing Systems Foundation, 2011. Print.
@inproceedings{2913412,
  abstract     = {The F-measure, originally introduced in information retrieval, is nowadays routinely used as a performance metric for problems such as binary classification, multi-label classification, and structured output prediction. Optimizing this measure remains a statistically and computationally challenging problem, since no closed-form maximizer exists. Current algorithms are approximate and typically rely on additional assumptions regarding the statistical distribution of the binary response variables. In this paper, we present an algorithm which is not only computationally efficient but also exact, regardless of the underlying distribution. The algorithm requires only a quadratic number of parameters of the joint distribution (with respect to the number of binary responses). We illustrate its practical performance by means of experimental results for multi-label classification.},
  author       = {Dembczy\'{n}ski, Krzysztof and Waegeman, Willem and Cheng, Weiwei and H{\"u}llermeier, Eyke},
  booktitle    = {Advances in Neural Information Processing Systems},
  editor       = {Shawe-Taylor, J and Zemel, RS and Bartlett, P and Pereira, F and Weinberger, KQ},
  issn         = {1049-5258},
  language     = {eng},
  location     = {Granada, Spain},
  pages        = {9},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {An exact algorithm for F-measure maximization},
  url          = {http://books.nips.cc/papers/files/nips24/NIPS2011\_0815.pdf},
  volume       = {24},
  year         = {2011},
}