Machine Learning

, Volume 83, Issue 2, pp 219–239 | Cite as

Relational information gain

  • Marco Lippi
  • Manfred Jaeger
  • Paolo Frasconi
  • Andrea Passerini


We introduce relational information gain, a refinement scoring function measuring the informativeness of newly introduced variables. The gain can be interpreted as a conditional entropy in a well-defined sense and can be efficiently approximately computed. In conjunction with simple greedy general-to-specific search algorithms such as FOIL, it yields an efficient and competitive algorithm in terms of predictive accuracy and compactness of the learned theory. In conjunction with the decision tree learner TILDE, it offers a beneficial alternative to lookahead, achieving similar performance while significantly reducing the number of evaluated literals.


Relational learning Inductive logic programming Information gain 


  1. Allauzen, C., Mohri, M., & Talwalkar, A. (2008). Sequence kernels for predicting protein essentiality. In Proceedings of the 25th international conference on machine learning (pp. 9–16). New York: ACM. CrossRefGoogle Scholar
  2. Blockeel, H., & De Raedt, L. (1997). Lookahead and discretization in ILP. In Proc. of the 7th int. workshop on ILP (pp. 77–84). Google Scholar
  3. Blockeel, H., & De Raedt, L. (1998). Top-down induction of first-order logical decision trees. Artificial intelligence, 101(1–2), 285–297. CrossRefzbMATHMathSciNetGoogle Scholar
  4. Castillo, L. P., & Wrobel, S. (2004). A comparative study on methods for reducing myopia of hill-climbing search in multirelational learning. In Proc. of the 21st int. conf. on machine learning. Google Scholar
  5. De Raedt, L. (1997). Logical settings for concept-learning. Artificial Intelligence, 95(1), 187–201. CrossRefzbMATHMathSciNetGoogle Scholar
  6. De Raedt, L. (2008). Logical and relational learning. Berlin: Springer. CrossRefzbMATHGoogle Scholar
  7. Fayyad, U. M., & Irani, K. B. (1992). On the handling of continuous-valued attributes in decision tree generation. Machine Learning, 8(1), 87–102. zbMATHGoogle Scholar
  8. Frasconi, P., Jaeger, M., & Passerini, A. (2008). Feature discovery with type extension trees. In Proc. of the 18th int. conf. on inductive logic programming (pp. 122–139). Google Scholar
  9. Gustafson, A. M., Snitkin, E. S., Parker, S. C. J., DeLisi, C., & Kasif, S. (2006). Towards the identification of essential genes using targeted genome sequencing and comparative analysis. BMC Genomics. Google Scholar
  10. Jensen, L. J., Kuhn, M., Stark, M., Chaffron, S., Creevey, C., Muller, J., Doerks, T., Julien, P., Roth, A., Simonovic, M., et al. (2009). STRING 8—a global view on proteins and their functional interactions in 630 organisms. Nucleic Acids Research, 37, D412. (Database issue). CrossRefGoogle Scholar
  11. Knobbe, A. J., Siebes, A., & van der Wallen, D. (1999). Multi-relational decision tree induction. In Proceedings of PKDD-99 (pp. 378–383). Google Scholar
  12. Landwehr, N., Gutmann, B., Thon, I., De Raedt, L., & Philipose, M. (2008). Relational transformation-based tagging for activity recognition. Fundamenta Informaticae, 89(1), 111–129. zbMATHGoogle Scholar
  13. Neville, J., Jensen, D., Friedland, L., & Hay, M. (2003). Learning relational probability trees. In Proceedings of SIGKDD’03. Google Scholar
  14. Perlich, C., & Provost, F. (2006). Distribution-based aggregation for relational learning with identifier attributes. Machine Learning, 62, 65–105. CrossRefGoogle Scholar
  15. Quinlan, J. R. (1991). Determinate literals in inductive logic programming. In J. Mylopoulos & R. Reiter (Eds.), Proc. of the 12th int. joint conf. on artificial intelligence. Google Scholar
  16. Quinlan, J. R., & Cameron-Jones, R. M. (1993). FOIL: A midterm report. In European conference on machine learning (p. 3). Berlin: Springer. Google Scholar
  17. Richardson, M., & Domingos, P. (2006). Markov logic networks. Machine Learning, 62(1–2), 107–136. CrossRefGoogle Scholar
  18. Struyf, J., Davis, J., & Page, D. (2006). An efficient approximation to lookahead in relational learners. In LNAI : Vol. 4212. Proceedings of ECML-06 (pp. 775–782). Berlin: Springer. Google Scholar
  19. Van Assche, A., Vens, C., Blockeel, H., & Dzeroski, S. (2006). First order random forests: learning relational classifiers with complex aggregates. Machine Learning, 64, 149–182. CrossRefzbMATHGoogle Scholar

Copyright information

© The Author(s) 2010

Authors and Affiliations

  • Marco Lippi
    • 1
  • Manfred Jaeger
    • 2
  • Paolo Frasconi
    • 1
  • Andrea Passerini
    • 3
  1. 1.Dipartimento di Sistemi e InformaticaUniversità degli Studi di FirenzeFlorenceItaly
  2. 2.Department for Computer ScienceAalborg UniversityAalborgDenmark
  3. 3.Dipartimento di Ingegneria e Scienza dell’InformazioneUniversità degli Studi di TrentoTrentoItaly

Personalised recommendations