Skip to main content

Advertisement

SpringerLink
Log in

Interactive Transfer Learning in Relational Domains

  • Technical Contribution
  • Published:
KI - Künstliche Intelligenz Aims and scope Submit manuscript

Abstract

We consider the problem of interactive transfer learning where a human expert provides guidance to the transfer learning algorithm that aims to transfer knowledge from a source task to a target task. One of the salient features of our approach is that we consider cross-domain transfer, i.e., transfer of knowledge across unrelated domains. We present an intuitive interface that allows for an expert to refine the knowledge in target task based on his/her expertise. Our results show that such guided transfer can effectively reduce the search space thus improving the efficiency and effectiveness of the transfer process.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. Note the difference between modes in ILP and modes of probability distributions. Modes inside ILP define the argument types of a predicate and help in the inductive search of the rules.

  2. We use the subscripts S to denote the source domain and T, the target domain respectively.

References

  1. Bilenko M, Mooney R (2003) Adaptive duplicate detection using learnable string similarity measures. In: ACM SIGKDD

  2. Carlson A, Betteridge J, Kisiel B, Settles B, Hruschka E Jr, Mitchell T (2010) Toward an architecture for never-ending language learning. In: AAAI

  3. Craven M, DiPasquo D, Freitag D, McCallum A, Mitchell T, Nigam K, Slattery S (1998) Learning to extract symbolic knowledge from the world wide web. AAAI

  4. Davis J, Domingos P (2009) Deep transfer via second-order markov logic. In: ICML

  5. De Raedt L, Frasconi P, Kersting K, Muggleton S (2008) Probabilistic inductive logic programming. Springer, New York

    Book  Google Scholar 

  6. Domingos P,  Lowd D (2009) Markov logic: an interface layer for artificial intelligence. Synthesis lectures on artificial intelligence and machine learning

  7. Getoor L, Taskar B (2007) Introduction to statistical relational learning. MIT Press, Cambridge

    Book  Google Scholar 

  8. Haaren J, Kolobov A, Davis J (2015) Todtler: two-order-deep transfer learning. In: AAAI

  9. Kersting K,  De Raedt L (2001) Bayesian logic programs. arXiv:cs/0111058

  10. Khot T, Natarajan S, Kersting K, Shavlik J (2011) Learning Markov logic networks via functional gradient boosting. In: ICDM

  11. Kumaraswamy R, Odom P, Kersting K, Leake D, Natarajan S (2015) Transfer learning via relational type matching. In: ICDM

  12. Mehta N, Natarajan S, Tadepalli P, Fern A  (2008) Transfer in variable-reward hierarchical reinforcement learning. Machine Learning

  13. Mihalkova L, Huynh T, Mooney R (2007) Mapping and revising markov logic networks for transfer learning. In: AAAI

  14. Mihalkova L, Mooney R (2007) Bottom-up learning of markov logic network structure. In: ICML

  15. Mihalkova L, Mooney R (2009) Transfer learning from minimal target data by mapping across relational domains. In: IJCAI

  16. Natarajan S, Tadepalli P, Dietterich TG, Fern A (2009) Learning first-order probabilistic models with combining rules. AMAI

  17. Odom P, Natarajan S (2016) Actively interacting with experts: A probabilistic logic approach. In: Joint European conference on machine learning and knowledge discovery in databases. Springer

  18. Ong IM, de Castro Dutra I, Page D, Costa VS (2005) Mode directed path finding. In: Gama J, Camacho R, Brazdil PB, Jorge AM, Torgo L (eds) Machine learning: ECML 2005. Lecture notes in computer science, vol 3720. Springer, Berlin, Heidelberg

    Google Scholar 

  19. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE transactions on knowledge and data engineering

  20. Raina R, Ng A, Koller D (2006) Constructing informative priors using transfer learning. In: Proceedings of the 23rd international conference on Machine learning. ACM

  21. Srinivasan A (2007) The aleph manual

  22. Torrey L, Shavlik J, Walker T, Maclin R (2008) Relational macros for transfer in reinforcement learning. In: Blockeel H, Ramon J, Shavlik J, Tadepalli P (eds) Inductive logic programming. ILP 2007. Lecture notes in computer science, vol 4894. Springer, Berlin, Heidelberg

    Google Scholar 

Download references

Acknowledgments

SN gratefully acknowledges the support of CwC Program Contract W911NF-15- 1-0461 with the US Defense Advanced Research Projects Agency (DARPA) and the Army Research Office (ARO). SN & NR gratefully acknowledge AFOSR award FA9550-18-1-0462. Any opinions, findings and conclusion or recommendations are those of the authors and do not necessarily reflect the view of the DARPA, ARO, AFOSR or the US government.

Author information

Authors and Affiliations

  1. Computing Science, University of Alberta, Edmonton, Canada

    Raksha Kumaraswamy

  2. Computer Science, University of Texas at Dallas, Richardson, USA

    Nandini Ramanan & Sriraam Natarajan

  3. Georgia Tech Research Institute, Georgia Institute of Technology, Atlanta, USA

    Phillip Odom

Authors
  1. Raksha Kumaraswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nandini Ramanan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Phillip Odom
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sriraam Natarajan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nandini Ramanan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumaraswamy, R., Ramanan, N., Odom, P. et al. Interactive Transfer Learning in Relational Domains. Künstl Intell 34, 181–192 (2020). https://doi.org/10.1007/s13218-020-00659-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13218-020-00659-6

Search

Navigation