GARUM: A Semantic Similarity Measure Based on Machine Learning and Entity Characteristics

  • Ignacio Traverso-RibónEmail author
  • Maria-Esther Vidal
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11029)


Knowledge graphs encode semantics that describes entities in terms of several characteristics, e.g., attributes, neighbors, class hierarchies, or association degrees. Several data-driven tasks, e.g., ranking, clustering, or link discovery, require for determining the relatedness between knowledge graph entities. However, state-of-the-art similarity measures may not consider all the characteristics of an entity to determine entity relatedness. We address the problem of similarity assessment between knowledge graph entities and devise GARUM, a semantic similarity measure for knowledge graphs. GARUM relies on similarities of entity characteristics and computes similarity values considering simultaneously several entity characteristics. This combination can be manually or automatically defined with the help of a machine learning approach. We empirically evaluate the accuracy of GARUM on knowledge graphs from different domains, e.g., networks of proteins and media news. In the experimental study, GARUM exhibits higher correlation with gold standards than studied existing approaches. Thus, these results suggest that similarity measures should not consider entity characteristics in isolation; contrary, combinations of these characteristics are required to precisely determine relatedness among entities in a knowledge graph. Further, the combination functions found by a machine learning approach outperform the results obtained by the manually defined aggregation functions.



This work has been partially funded by the EU H2020 Programme for the Project No. 727658 (IASIS).


  1. 1.
    Benik, J., Chang, C., Raschid, L., Vidal, M.-E., Palma, G., Thor, A.: Finding cross genome patterns in annotation graphs. In: Bodenreider, O., Rance, B. (eds.) DILS 2012. LNCS, vol. 7348, pp. 21–36. Springer, Heidelberg (2012). Scholar
  2. 2.
    Gene Ontology Consortium, et al.: Gene ontology consortium: going forward. Nucleic Acids Res. 43(D1), D1049–D1056 (2015)Google Scholar
  3. 3.
    Couto, F.M., Silva, M.J., Coutinho, P.M.: Measuring semantic similarity between Gene Ontology terms. Data Knowl. Eng. 61(1), 137–152 (2007)CrossRefGoogle Scholar
  4. 4.
    Damljanovic, D., Stankovic, M., Laublet, P.: Linked data-based concept recommendation: comparison of different methods in open innovation scenario. In: Simperl, E., Cimiano, P., Polleres, A., Corcho, O., Presutti, V. (eds.) ESWC 2012. LNCS, vol. 7295, pp. 24–38. Springer, Heidelberg (2012). Scholar
  5. 5.
    Devos, D., Valencia, A.: Practical limits of function prediction. Prot.: Struct. Funct. Bioinform. 41(1), 98–107 (2000)Google Scholar
  6. 6.
    Gabrilovich, E., Markovitch, S.: Computing semantic relatedness using Wikipedia-based explicit semantic analysis. In: IJCAI, vol. 7, pp. 1606–1611 (2007)Google Scholar
  7. 7.
    Hassan, S., Mihalcea, R.: Semantic relatedness using salient semantic analysis. In: AAAI (2011)Google Scholar
  8. 8.
    Jiang, J.J., Conrath, D.W.: Semantic similarity based on corpus statistics and lexical taxonomy. arXiv preprint arXiv:cmp-lg/9709008 (1997)
  9. 9.
    Kazakov, Y.: SRIQ and SROIQ are harder than SHOIQ. In: Description Logics. CEUR Workshop Proceedings, vol. 353. (2008)Google Scholar
  10. 10.
    Köhler, S., et al.: The Human Phenotype Ontology project: linking molecular biology and disease through phenotype data. Nucleic Acids Res. 42(D1), D966–D974 (2014)CrossRefGoogle Scholar
  11. 11.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Log. Q. 2(1–2), 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Landauer, T.K., Laham, D., Rehder, B., Schreiner, M.E.: How well can passage meaning be derived without using word order? A comparison of Latent Semantic Analysis and humans. In: Proceedings of the 19th annual meeting of the Cognitive Science Society, pp. 412–417 (1997)Google Scholar
  13. 13.
    Lee, M., Pincombe, B., Welsh, M.: An empirical evaluation of models of text document similarity. In: Cognitive Science (2005)Google Scholar
  14. 14.
    Lin, D.: An information-theoretic definition of similarity. In: ICML, vol. 98, pp. 296–304 (1998)Google Scholar
  15. 15.
    Paul, C., Rettinger, A., Mogadala, A., Knoblock, C.A., Szekely, P.: Efficient graph-based document similarity. In: Sack, H., Blomqvist, E., d’Aquin, M., Ghidini, C., Ponzetto, S.P., Lange, C. (eds.) ESWC 2016. LNCS, vol. 9678, pp. 334–349. Springer, Cham (2016). Scholar
  16. 16.
    Pekar, V., Staab, S.: Taxonomy learning: factoring the structure of a taxonomy into a semantic classification decision. In: Proceedings of the 19th International Conference on Computational Linguistics, vol. 1, pp. 1–7. Association for Computational Linguistics (2002)Google Scholar
  17. 17.
    Pesquita, C., Faria, D., Bastos, H., Falcão, A., Couto, F.: Evaluating go-based semantic similarity measures. In: Proceedings of 10th Annual Bio-Ontologies Meeting, vol. 37, p. 38 (2007)Google Scholar
  18. 18.
    Pesquita, C., Pessoa, D., Faria, D., Couto, F.: CESSM: collaborative evaluation of semantic similarity measures. JB2009: Chall. Bioinform. 157, 190 (2009)Google Scholar
  19. 19.
    Resnik, P., et al.: Semantic similarity in a taxonomy: an information-based measure and its application to problems of ambiguity in natural language. J. Artif. Intell. Res. (JAIR) 11, 95–130 (1999)CrossRefGoogle Scholar
  20. 20.
    Schuhmacher, M., Ponzetto, S.P.: Knowledge-based graph document modeling. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining, pp. 543–552. ACM (2014)Google Scholar
  21. 21.
    Sevilla, J.L., et al.: Correlation between gene expression and GO semantic similarity. IEEE/ACM Trans. Comput. Biol. Bioinform. 2(4), 330–338 (2005)CrossRefGoogle Scholar
  22. 22.
    Shi, C., Kong, X., Huang, Y., Yu, P.S., Wu, B.: HeteSim: a general framework for relevance measure in heterogeneous networks. IEEE Trans. Knowl. Data Eng. 26(10), 2479–2492 (2014)CrossRefGoogle Scholar
  23. 23.
    Smith, T.F., Waterman, M.S.: Identification of common molecular subsequences. J. Mol. Biol. 147(1), 195–197 (1981)CrossRefGoogle Scholar
  24. 24.
    Sun, Y., Han, J., Yan, X., Yu, P.S., Wu, T.: PathSim: meta path-based top-k similarity search in heterogeneous information networks. In: VLDB 2011 (2011)Google Scholar
  25. 25.
    Traverso-Ribón, I., Vidal, M.: Exploiting information content and semantics to accurately compute similarity of GO-based annotated entities. In: IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB, pp. 1–8 (2015)Google Scholar
  26. 26.
    Traverso-Ribón, I., Vidal, M.-E., Palma, G.: OnSim: a similarity measure for determining relatedness between ontology terms. In: Ashish, N., Ambite, J.-L. (eds.) DILS 2015. LNCS, vol. 9162, pp. 70–86. Springer, Cham (2015). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.University of CadizCádizSpain
  2. 2.L3S Research CenterHanoverGermany
  3. 3.TIB Leibniz Information Center for Science and TechnologyHanoverGermany

Personalised recommendations