Abstract
Conventional machine learning methods assume data to be independent and identically distributed (i.i.d.) and ignore the relational structure of the data, which contains crucial information about how objects participate in relationships and events. Statistical Relational Learning (SRL) combines elements from statistical and probabilistic modeling to relational learning to represent and learn in domains with complex relational and rich probabilistic structures. SRL models do not suppose data to be i.i.d., but, as conventional machine learning models, they also assume training and testing data are sampled from the same distribution. Transfer learning has emerged as an essential technique to handle scenarios where such an assumption does not hold. It aims to provide methods with the ability to recognize knowledge previously learned in a source domain and apply it to a new model in a target domain to start solving a new task. For SRL models, the primary challenge is to transfer the learned structure, mapping the vocabulary across different domains. In this work, we propose TransBoostler, an algorithm that uses pre-trained word embeddings to guide the mapping. We follow the assumption that the name of a predicate has a semantic connotation that can be mapped to a vector space model. Next, TransBoostler employs theory revision to adapt the mapped model to the target data. Experimental results showed that TransBoostler successfully transferred trees across different domains. It performs equally well as, or better than, previous systems and requires less training time for some investigated scenarios.
Similar content being viewed by others
Data availability
The data is publicly available at https://github.com/MeLLL-UFF/TransBoostler.
Code availability
The code is available at https://github.com/MeLLL-UFF/TransBoostler.
Notes
The source code and experiments are publicly available at https://github.com/MeLL-UFF/TransBoostler.
Munich Information Center of Protein Sequence.
References
Azevedo Santos, R., Paes, A., & Zaverucha, G. (2020). Transfer learning by mapping and revising boosted relational dependency networks. Mach Learn, 109(7), 1435–1463. https://doi.org/10.1007/s10994-020-05871-x
Baziotis, C., Pelekis, N., & Doulkeridis, C. (2017). Deep lstm with attention for message-level and topic-based sentiment analysis. In: Proc. of the 11th Int. Workshop on Semantic Evaluation (SemEval-2017). Association for Computational Linguistics, Vancouver, Canada, pp 747–754
Bilenko, M., & Mooney, RJ. (2003). Adaptive duplicate detection using learnable string similarity measures. In: Proc. of the Ninth ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining. Association for Computing Machinery, New York, NY, USA, KDD ’03, p 39-48, https://doi.org/10.1145/956750.956759
Bojanowski, P., Grave, E., Joulin, A., et al. (2017). Enriching Word Vectors with Subword Information. Trans of the Association for Computational Linguistics, 5, 135–146. https://doi.org/10.1162/tacl_a_00051 https://arxiv.org/abs/https://direct.mit.edu/tacl/articlepdf/doi/10.1162/tacl a 00051/1567442/tacl a 00051.pdf
Bordes, A., Usunier, N., & Garcia-Duran, A., et al. (2013). Translating embeddings for modeling multi-relational data. In: Burges C, Bottou L, Welling M, et al (eds) Advances in Neural Information Processing Systems, vol 26. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2013/file/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf
Bratko, I. (1990). PROLOG programming for artificial intelligence (2nd ed.). Inc, USA: Addison-Wesley Longman Publishing Co.
Carlson, A., Betteridge, J., Kisiel, B., & et al. (2010). Toward an architecture for never-ending language learning. In: Proc. of the Twenty-Fourth AAAI Conf. on Artificial Intelligence. AAAI Press, AAAI’10, p 1306-1313
Davis, J., & Goadrich, M. (2006). The relationship between precision-recall and roc curves. In: Proc. of the 23rd Int. Conf. on Mach. Learn. Association for Computing Machinery, New York, NY, USA, ICML ’06, p 233-240, https://doi.org/10.1145/1143844.1143874
De Raedt, L. (2008). Logical and Relational Learning. pp 1–1, https://doi.org/10.1007/978-3-540-88190-2_1
Dietterich, TG., Ashenfelter, A., & Bulatov, Y. (2004). Training conditional random fields via gradient tree boosting. In: Proc. of the Twenty-First Int. Conf. on Mach. Learn. Association for Computing Machinery, New York, NY, USA, ICML ’04, p 28, https://doi.org/10.1145/1015330.1015428
Duboc, A. L., Paes, A., & Zaverucha, G. (2009). Using the bottom clause and mode declarations in fol theory revision from examples. Machine Learning, 76(1), 73–107.
de Figueiredo, L. F., Paes, A., & Zaverucha, G. (2022). Transfer learning for boosted relational dependency networks through genetic algorithm. In N. Katzouris & A. Artikis (Eds.), Inductive Logic Programming (pp. 125–139). Springer Int: Publishing, Cham.
Friedman, N., Getoor, L., Koller, D., & et al. (1999). Learning probabilistic relational models. In: Proc. of the 16th Int. Joint Conf. on Artificial Intelligence - Volume 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI’99, p 1300-1307
Getoor, L., & Taskar, B. (2007). Introduction to Statistical Relational Learning (Adapt. Computation and Mach. Learn.). The MIT Press
Haaren, JV., Kolobov, A., & Davis, J. (2015). Todtler: Two-order-deep transfer learning. In: Proc. of the Twenty-Ninth AAAI Conference on Artificial Intelligence. AAAI Press, AAAI’15, p 3007-3015
Han, X., Huang, Z., An, B., & et al. (2021). Adaptive transfer learning on graph neural networks. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. Association for Computing Machinery, New York, NY, USA, p 565-574
Hirsch, S., Guy, I., Nus, A., & et al. (2020). Query reformulation in e-commerce search. In: Proc. of the 43rd Int. ACM SIGIR Conf. on Research and Development in Information Retrieval. Association for Computing Machinery, New York, NY, USA, p 1319-1328, https://doi.org/10.1145/3397271.3401065
Khosravi, H., & Bina, B. (2010). A survey on statistical relational learning. In: Proc. of the 23rd Canadian Conf. on Adv. in Artificial Intelligence. Springer-Verlag, Berlin, Heidelberg, AI’10, p 256-268, https://doi.org/10.1007/978-3-642-13059-5_25
Khosravi, H., Schulte, O., Hu, J., et al. (2012). Learning compact markov logic networks with decision trees. In S. H. Muggleton, A. Tamaddoni-Nezhad, & F. A. Lisi (Eds.), Inductive Logic Programming (pp. 20–25). Berlin Heidelberg, Berlin, Heidelberg: Springer.
Kuhn, H. W. (1955). The Hungarian Method for the Assignment Problem. Naval Research Logistics Quarterly, 2(1–2), 83–97. https://doi.org/10.1002/nav.3800020109
Kumaraswamy, R., Odom, P., Kersting, K., & et al. (2015). Transfer learning via relational type matching. In: 2015 IEEE Int. Conf. on Data Mining, pp 811–816, https://doi.org/10.1109/ICDM.2015.138
Kusner, M., Sun, Y., Kolkin, N., & et al. (2015). From word embeddings to document distances. In: Bach F, Blei D (eds) Proc. of the 32nd Int. Conf. on Mach. Learn., Proc. of Mach. Learn. Res., vol 37. PMLR, Lille, France, pp 957–966
Lee, C. K., Lu, C., Yu, Y., et al. (2021). Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers. The Journal of Chemical Physics, 154(2), 024–906.
Luca, T., Paes, A., & Zaverucha, G. (2022). Mapping across relational domains for transfer learning with word embeddings-based similarity. In N. Katzouris & A. Artikis (Eds.), Inductive Logic Programming (pp. 167–182). Springer Int: Publishing, Cham.
Mewes, H. W., Frishman, D., Gruber, C., et al. (2000). Mips: A database for genomes and protein sequences. Nucleic Acids Research, 28, 37–40. https://doi.org/10.1093/nar/28.1.37
Mihalkova, L., & Mooney, RJ. (2007). Bottom-up learning of markov logic network structure. In: Proc. of the 24th Int. Conf. on Mach. Learn. Association for Computing Machinery, New York, NY, USA, ICML ’07, p 625-632, https://doi.org/10.1145/1273496.1273575
Mihalkova, L., & Mooney, RJ. (2009). Transfer learning from minimal target data by mapping across relational domains. In: Proc. of the 21st Int. Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, IJCAI’09, p 1163-1168
Mihalkova, L., Huynh, T., & Mooney, RJ. (2007). Mapping and revising markov logic networks for transfer learning. In: Proc. of the 22nd Nat. Conf. on Artificial Intelligence - Volume 1. AAAI Press, AAAI’07, p 608-614
Mikolov, T., Chen, K., Corrado, G., & et al. (2013a). Efficient estimation of word representations in vector space. In: Bengio Y, LeCun Y (eds) 1st Int. Conf. on Learn. Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings
Mikolov, T., Sutskever, I., Chen, K., et al. (2013b). Distributed representations of words and phrases and their compositionality. In: Proc. of the 26th Int. Conf. on Neural Information Processing Systems - Volume 2. Curran Associates Inc., Red Hook, NY, USA, NIPS’13, p 3111-3119
Mikolov, T., Grave, E., Bojanowski, P., & et al. (2018). Advances in pre-training distributed word representations. In: Proc. of the Eleventh Int. Conf. on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan, https://aclanthology.org/L18-1008
Miller, G. A. (1995). Wordnet: A lexical database for English. Communications ACM, 38(11), 39–41. https://doi.org/10.1145/219717.219748
Natarajan, S., Khot, T., Kersting, K., et al. (2012). Gradient-based boosting for statistical relational learning: The relational dependency network case. Machine Learning, 86(1), 25–56. https://doi.org/10.1007/s10994-011-5244-9
Neville, J., & Jensen, D. (2007). Relational dependency networks. Journal Machine Learning Research, 8, 653–692.
Paes, A., Zaverucha, G., & Costa, V. S. (2017). On the use of stochastic local search techniques to revise first-order logic theories from examples. Machine Learning, 106(2), 197–241. https://doi.org/10.1007/s10994-016-5595-3
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191
Pele, O., & Werman, M. (2009). Fast and robust earth mover’s distances. In: 2009 IEEE 12th Int. Conf. on Computer Vision, pp 460–467, https://doi.org/10.1109/ICCV.2009.5459199
Pilehvar, M. T., & Camacho-Collados, J. (2020). Embeddings in natural language processing: Theory and advances in vector representations of meaning. Synthesis Lectures on Human Language Technologies, 13(4), 1–175. https://doi.org/10.2200/S01057ED1V01Y202009HLT047
Shvaytser, H. (1990). A necessary condition for learning from positive examples. Machine Learning, 5(1), 101–113.
Sidorov, G., Gelbukh, A., Gomez, Adorno, H., & et al. (2014). Soft similarity and soft cosine measure: Similarity of features in vector space model. Computación y Sistemas 18. https://doi.org/10.13053/cys-18-3-2043
Stahl, I. (1993). Predicate invention in ilp-an overview. In: European Conference on Machine Learning, Springer, pp 311–322
Tan, C., Sun, F., Kong, T., & et al. (2018). A survey on deep transfer learning. In: Kurková V, Manolopoulos Y, Hammer B, et al (eds) Artificial Neural Networks and Mach. Learn. - ICANN 2018 - 27th Int. Conf. on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proc., Part III, Lecture Notes in Computer Science, vol 11141. Springer, pp 270–279, https://doi.org/10.1007/978-3-030-01424-7_27
Torregrossa, F., Allesiardo, R., Claveau, V., et al. (2021). A survey on training and evaluation of word embeddings. Int Journal of Data Science and Analytics, 11(2), 85–103. https://hal.archives-ouvertes.fr/hal-03148517
Torrey, L., & Shavlik, J. (2010). Transfer learning. In: Handbook of research on Mach. Learn. applications and trends: algorithms, methods, and techniques. IGI global, pp 242–264
Toutanova, K., Klein, D., Manning, CD., & et al. (2003). Feature-rich part-of-speech tagging with a cyclic dependency network. In: Proc. of the 2003 Conf. of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1. Association for Computational Linguistics, USA, NAACL ’03, p 173-180, https://doi.org/10.3115/1073445.1073478
Valiant, L. G. (1984). A theory of the learnable. Communications of the ACM, 27(11), 1134–1142.
Vig, L., Srinivasan, A., Bain, M., et al. (2017). An investigation into the role of domain-knowledge on the use of embeddings. Int Conf. on Inductive Logic Programming (pp. 169–183). Springer.
Wang, Z., Zhang, J., Feng, J., & et al. (2014). Knowledge graph embedding by translating on hyperplanes. In: Proc. of the AAAI Conf. on Artificial Intelligence
Wrobel, S. (1996). First Order Theory Refinement. In L. De Raedt (Ed.), Advances in Inductive Logic Programming. IOS Press.
Wu, Z., Zhao, D., Liang, Q., & et al. (2021). Dynamic sparsity neural networks for automatic speech recognition. In: IEEE Int. Conf. on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021. IEEE, pp 6014–6018, https://doi.org/10.1109/ICASSP39728.2021.9414505
Yang, Q., Zhang, Y., Dai, W., et al. (2020). Transfer Learning. Cambridge University Press. https://doi.org/10.1017/9781139061773
Acknowledgements
We would like to thank the Brazilian Research Agencies CAPES, CNPq (311275/2020-6 (AP) and 308376/2021-8 (GZ)), and FAPERJ (E-26/202.914/2019 (247109) (AP)) for financial support. Thanks to the authors of RDN-B and TreeBoostler for the available code and the help with doubts. We also thank the authors of the datasets and the anonymous reviewers for their valuable feedback.
Funding
This work was partially funded by CNPq, FAPERJ, and CAPES.
Author information
Authors and Affiliations
Contributions
All authors contributed to building ideas and reaching the research goals and aims, and; the development and design of the methodology used in this work. All authors were committed to the application of statistical and computational techniques as well as verifying the experimental results and other research outputs. Thais Luca was responsible for designing the computer programs, software development, and implementing the code used during research. Thais was also responsible for other activities such as conducting the research and performing the experiments, and; preparing and creating the published work. Aline Paes and Gerson Zaverucha were responsible for supervising the research activity, mentorship, coordinating research activity planning and execution, and acquisition of the financial support for the project leading to this publication
Corresponding author
Ethics declarations
Conflict of interest
Not applicable. There is no conflict of interests.
Ethicaal approval
Not applicable. The research conduct here does not require ethics approval.
Consent to participate
Not applicable. This manuscript does not conduct any research with individuals.
Consent for publication
Not applicable. All images in the manuscript are produced by the authors.
Additional information
Editors: Alireza Tamaddoni-Nezhad, Alan Bundy, Luc De Raedt, Artur d’Avila Garcez, Sebastijan Dumančić, Cèsar Ferri, Pascal Hitzler, Nikos Katzouris, Denis Mareschal, Stephen Muggleton, Ute Schmid.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A Mapping algorithms
Appendix A Mapping algorithms
1.1 A.1 Depth-first mapping algorithm
We present the algorithm of the Depth-first mapping approach. As source predicates appear in the tree structure, it computes similarities with target predicates to return its most similar.
1.2 A.2 Ranked-first mapping algorithm
We present the algorithm of the Ranked-first mapping approach. First, it computes all similarities between pairs of source and target predicates. Then, it follows such an ordered list to map the most similar predicates.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Luca, T., Paes, A. & Zaverucha, G. Word embeddings-based transfer learning for boosted relational dependency networks. Mach Learn 113, 1269–1302 (2024). https://doi.org/10.1007/s10994-023-06404-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10994-023-06404-y