Advanced search
1 file | 195.36 KB Add to list

Conditional ranking on relational data

Author
Organization
Abstract
In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel framework for learning conditional rankings from various types of relational data, where rankings can be conditioned on unseen data objects. Conditional ranking from symmetric or reciprocal relations can in this framework be treated as two important special cases. Furthermore, we propose an efficient algorithm for conditional ranking by optimizing a squared ranking loss function. Experiments on synthetic and real-world data illustrate that such an approach delivers state-of-the-art performance in terms of predictive power and computational complexity. Moreover, we also show empirically that incorporating domain knowledge in the model about the underlying relations can improve the generalization performance.

Downloads

  • pahikkala 730.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 195.36 KB

Citation

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

MLA
Pahikkala, Tapio, Willem Waegeman, Antti Airola, et al. “Conditional Ranking on Relational Data.” Lecture Notes in Artificial Intelligence. Ed. José Luis Balcázar et al. Vol. 6322. Berlin, Germany: Springer, 2010. 499–514. Print.
APA
Pahikkala, T., Waegeman, W., Airola, A., Salakoski, T., & De Baets, B. (2010). Conditional ranking on relational data. In J. L. Balcázar, F. Bonchi, A. Gionis, & M. Sebag (Eds.), Lecture Notes in Artificial Intelligence (Vol. 6322, pp. 499–514). Presented at the European conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2010), Berlin, Germany: Springer.
Chicago author-date
Pahikkala, Tapio, Willem Waegeman, Antti Airola, Tapio Salakoski, and Bernard De Baets. 2010. “Conditional Ranking on Relational Data.” In Lecture Notes in Artificial Intelligence, ed. José Luis Balcázar, Francesco Bonchi, Aristides Gionis, and Michèle Sebag, 6322:499–514. Berlin, Germany: Springer.
Chicago author-date (all authors)
Pahikkala, Tapio, Willem Waegeman, Antti Airola, Tapio Salakoski, and Bernard De Baets. 2010. “Conditional Ranking on Relational Data.” In Lecture Notes in Artificial Intelligence, ed. José Luis Balcázar, Francesco Bonchi, Aristides Gionis, and Michèle Sebag, 6322:499–514. Berlin, Germany: Springer.
Vancouver
1.
Pahikkala T, Waegeman W, Airola A, Salakoski T, De Baets B. Conditional ranking on relational data. In: Balcázar JL, Bonchi F, Gionis A, Sebag M, editors. Lecture Notes in Artificial Intelligence. Berlin, Germany: Springer; 2010. p. 499–514.
IEEE
[1]
T. Pahikkala, W. Waegeman, A. Airola, T. Salakoski, and B. De Baets, “Conditional ranking on relational data,” in Lecture Notes in Artificial Intelligence, Barcelona, Spain, 2010, vol. 6322, pp. 499–514.
@inproceedings{1155388,
  abstract     = {In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel framework for learning conditional rankings from various types of relational data, where rankings can be conditioned on unseen data objects. Conditional ranking from symmetric or reciprocal relations can in this framework be treated as two important special cases. Furthermore, we propose an efficient algorithm for conditional ranking by optimizing a squared ranking loss function. Experiments on synthetic and real-world data illustrate that such an approach delivers state-of-the-art performance in terms of predictive power and computational complexity. Moreover, we also show empirically that incorporating domain knowledge in the model about the underlying relations can improve the generalization performance.},
  author       = {Pahikkala, Tapio and Waegeman, Willem and Airola, Antti and Salakoski, Tapio and De Baets, Bernard},
  booktitle    = {Lecture Notes in Artificial Intelligence},
  editor       = {Balcázar, José Luis and Bonchi, Francesco and Gionis, Aristides and Sebag, Michèle},
  isbn         = {9783642158827},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Barcelona, Spain},
  pages        = {499--514},
  publisher    = {Springer},
  title        = {Conditional ranking on relational data},
  url          = {http://dx.doi.org/10.1007/978-3-642-15883-4_32},
  volume       = {6322},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: