Advertisement

A Semantic Use Case Simulation Framework for Training Machine Learning Algorithms

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11313)

Abstract

To train autonomous agents, large training data sets are required to provide the necessary support in solving real-world problems. In domains such as healthcare or ambient assisted living, such training sets are often incomplete or do not cover the unique requirements and constraints of specific use cases, leading to the cold-start problem. This work describes a semantic simulation framework that generates qualitative use case specific data for Machine-Learning (ML) driven agents, thus solving the cold-start problem. By combing simulated data with axiomatically formalized use case requirements, we are able to train ML algorithms without real-world data at hand. We integrate domain specific guidelines and their semantic representation by using SHACL/RDF(S) and SPARQL CONSTRUCT queries. The main benefits of this approach are (1) portability to other domains, (2) applicability to various ML algorithms, and (3) mitigation of the cold-start problem or sparse data.

Keywords

Simulation Framework Training ML Algorithms Cold Start Problem SPARQL CONSTRUCT Queries Shapes Constraint Language (SHACL) 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgement

This work is supported by the European Union (H2020) under the vCare project (grant agreement No. 769807).

References

  1. 1.
    Mariappan, A.K., Sobhanam, H.: A hybrid approach to solve cold start problem in recommender systems using association rules and clustering technique. Int. J. Comput. Appl. 74(4), 17–23 (2013)Google Scholar
  2. 2.
    Carlson, A., et al.: Toward an architecture for never-ending language learning. In: AAAI. vol. 5, p. 3. Atlanta (2010)Google Scholar
  3. 3.
    Di Noia, T., Ostuni, V.C.: Recommender systems and linked open data. In: Faber, W., Paschke, A. (eds.) Reasoning Web 2015. LNCS, vol. 9203, pp. 88–113. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-21768-0_4CrossRefGoogle Scholar
  4. 4.
    Godoy, D., Amandi, A.: An agent-based recommender system to support collaborative web search based on shared user interests. In: Haake, J.M., Ochoa, S.F., Cechich, A. (eds.) CRIWG 2007. LNCS, vol. 4715, pp. 303–318. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-74812-0_24CrossRefGoogle Scholar
  5. 5.
    Lika, B., Kolomvatsos, K., Hadjiefthymiades, S.: Facing the cold start problem in recommender systems. Expert. Syst. Appl. 41(4, Part 2), 2065–2073 (2014).  https://doi.org/10.1016/j.eswa.2013.09.005CrossRefGoogle Scholar
  6. 6.
    Mantrach, A.: Cold start solutions for recommender systems. https://research.yahoo.com/_c/uploads/SeminarUCSD.pdf
  7. 7.
    Mehta, R., Rana, K.: A review on matrix factorization techniques in recommender systems. In: 2017 2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA), pp. 269–274, April 2017Google Scholar
  8. 8.
    Middleton, S.E., Alani, H., Roure, D.D.: Exploiting synergy between ontologies and recommender systems. CoRR arXiv:cs/0204012 (2002)
  9. 9.
    Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR arXiv:cs/0204012 (2013)
  10. 10.
    Musto, C.: Introducing linked open data in graph-based recommender systems. Inf. Process. Manag. 53(2), 405–435 (2017).  https://doi.org/10.1016/j.ipm.2016.12.003CrossRefGoogle Scholar
  11. 11.
    Nouali, O., Belloui, A.: Using semantic web to reduce the cold-start problems in recommendation systems. In: 2009 Second International Conference on the Applications of Digital Information and Web Technologies, pp. 525–530, August 2009Google Scholar
  12. 12.
    Palau, J., Montaner, M., López, B., de la Rosa, J.L.: Collaboration analysis in recommender systems using social networks. In: Klusch, M., Ossowski, S., Kashyap, V., Unland, R. (eds.) CIA 2004. LNCS (LNAI), vol. 3191, pp. 137–151. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-30104-2_11CrossRefGoogle Scholar
  13. 13.
    Peis, E., et al.: Semantic recommender systems. Analysis of the state of the topic. Hipertext.net 6 (2008). http://hipertext.net/english/pag1031.htm
  14. 14.
    Rubens, N., Elahi, M., Sugiyama, M., Kaplan, D.: Active learning in recommender systems. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 809–846. Springer, Boston, MA (2015).  https://doi.org/10.1007/978-1-4899-7637-6_24CrossRefGoogle Scholar
  15. 15.
    Schein, A.I., Popescul, A., Unger, L.H., Pennock, D.M.: Methods and metrics for cold-start recommendations. In: Proceedings of SIGIR 2002, pp. 253–260. Tampere, Finland (2002).  https://doi.org/10.1145/564376.564421
  16. 16.
    Settles, B.: Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin-Madison (2010). http://axon.cs.byu.edu/~martinez/classes/778/Papers/settles.activelearning.pdf
  17. 17.
    Son, L.H.: Dealing with the new user cold-start problem in recommender systems: a comparative review. Inf. Syst. 58, 87–104 (2016). http://www.sciencedirect.com/science/article/pii/S0306437914001525CrossRefGoogle Scholar
  18. 18.
    Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge, MA, USA (1998)Google Scholar
  19. 19.
    Thanh-Tai, H., Nguyen, H.-H., Thai-Nghe, N.: A semantic approach in recommender systems. In: Dang, T.K., Wagner, R., Küng, J., Thoai, N., Takizawa, M., Neuhold, E. (eds.) FDSE 2016. LNCS, vol. 10018, pp. 331–343. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48057-2_23CrossRefGoogle Scholar
  20. 20.
    Tomeo, P., et al.: Exploiting linked open data in cold-start recommendations with positive-only feedback. In: Proceedings of the 4th Spanish Conference on Information Retrieval. pp. 11:1–11:8. CERI 2016. ACM, New York (2016).  https://doi.org/10.1145/2934732.2934745
  21. 21.
    Yang, R.: Using semantic technology to improve recommender systems based on slope one. In: Li, J., Qi, G., Zhao, D., Nejdl, W., Zheng, H.T. (eds.) Semantic Web and Web Science, pp. 11–23. Springer, New York (2012).  https://doi.org/10.1007/978-1-4614-6880-6_2CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Information Process EngineeringFZI Forschungszentrum Informatik am KITKarlsruheGermany
  2. 2.Institute for Computer ScienceUniversity of Applied Sciences DarmstadtDarmstadtGermany

Personalised recommendations