Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are metalearning and transfer learning. Metalearning can be used for selecting the predictive model to use on a new dataset. Transfer learning allows the reuse of knowledge from previous tasks. However, when multiple heterogeneous tasks are available as potential sources for transfer, the question is which one to use. One approach to address this problem is metalearning. In this paper we investigate the feasibility of this approach. We propose a method to transfer weights from a source trained neural network to initialize a network that models a potentially very different target dataset. Our experiments with 14 datasets indicate that this method enables faster convergence without significant difference in accuracy provided that the source task is adequately chosen. This means that there is potential for applying metalearning to support transfer between heterogeneous datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brazdil, P., Giraud-Carrier, C.G., Soares, C., Vilalta, R.: Metalearning - Applications to Data Mining. Cognitive Technologies. Springer, Berlin (2009)
Rice, J.R.: The algorithm selection problem. Adv. Comput. 15, 65–118 (1976)
Brazdil, P., Soares, C., da Costa, J.P.: Ranking learning algorithms: using IBL and meta-learning on accuracy and time results. Mach. Learn. 50(3), 251–277 (2003)
Gama, J., Brazdil, P.: Characterization of classification algorithms. In: Pinto-Ferreira, C., Mamede, N.J. (eds.) EPIA 1995. LNCS (LNAI), vol. 990, pp. 189–200. Springer, Heidelberg (1995)
Prudêncio, R.B.C., Ludermir, T.B.: Meta-learning approaches to selecting time series models. Neurocomputing 61, 121–137 (2004)
Gomes, T.A.F., Prudêncio, R.B.C., Soares, C., Rossi, A.L.D., Carvalho, A.C.P.L.F.: Combining meta-learning and search techniques to select parameters for support vector machines. Neurocomputing 75(1), 3–13 (2012)
Serban, F., Vanschoren, J., Kietz, J.U., Bernstein, A.: A survey of intelligent assistants for data analysis. ACM Comput. Surv. 45(3), 31:1–31:35 (2013)
Abreu, P., Soares, C., Valente, J.M.S.: Selection of heuristics for the job-shop scheduling problem based on the prediction of gaps in machines. In: Stützle, T. (ed.) LION 3. LNCS, vol. 5851, pp. 134–147. Springer, Heidelberg (2009)
Smith-Miles, K.: Cross-disciplinary perspectives on meta-learning for algorithm selection. ACM Comput. Surv. 41(1), 6:1–6:25 (2009)
Gama, J., Kosina, P.: Learning about the learning process. In: Gama, J., Bradley, E., Hollmén, J. (eds.) IDA 2011. LNCS, vol. 7014, pp. 162–172. Springer, Heidelberg (2011)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Dai, W., Yang, Q., Xue, G., Yu, Y.: Boosting for transfer learning. In: Proceedings of the Twenty-Fourth International Conference on Machine Learning (ICML 2007), pp. 193–200, Corvallis, Oregon, USA, 20–24 June 2007
Blitzer, J., McDonald, R., Pereira, F.: Domain adaptation with structural correspondence learning. In: Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pp. 120–128. Association for Computational Linguistics (2006)
Gao, J., Fan, W., Jiang, J., Han, J.: Knowledge transfer via multiple model local structure mapping. In: International Conference on Knowledge Discovery and Data Mining, Las Vegas, NV (2008)
Mihalkova, L., Huynh, T., Mooney, R.J.: Mapping and revising markov logic networks for transfer learning. In: Proceedings of the 22nd National Conference on Artificial Intelligence, pp. 608–614. AAAI (2007)
Pratt, L.Y., Pratt, L.Y., Hanson, S.J., Giles, C.L., Cowan, J.D.: Discriminability-based transfer between neural networks. In: Advances in Neural Information Processing Systems 5, pp. 204–211. Morgan Kaufmann (1993)
Silver, D.L., Poirier, R., Currie, D.: Inductive transfer with context-sensitive neural networks. Mach. Learn. 73(3), 313–336 (2008)
Rosenstein, M.T., Marx, Z., Kaelbling, L.P., Dietterich, T.G.: To transfer or not to transfer. In: NIPS 2005 Workshop, Inductive Transfer: 10 Years Later (2005)
Ramon, J., Driessens, K., Croonenborghs, T.: Transfer learning in reinforcement learning problems through partial policy recycling. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladenič, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 699–707. Springer, Heidelberg (2007)
Mahmud, M., Ray, S.: Transfer learning using kolmogorov complexity: basic theory and empirical evaluations. In: Advances in Neural Information Processing Systems, pp. 985–992 (2007)
Eaton, E., desJardins, M., Lane, T.: Modeling transfer relationships between learning tasks for improved inductive transfer. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008, Part I. LNCS (LNAI), vol. 5211, pp. 317–332. Springer, Heidelberg (2008)
Biondi, G., Prati, R.: Setting parameters for support vector machines using transfer learning. J. Intell. Robot. Syst. 80(1), 295–311 (2015)
Aiolli, F.: Transfer learning by kernel meta-learning. In: ICML Unsupervised and Transfer Learning, pp. 81–95 (2012)
Do, C., Ng, A.Y.: Transfer learning for text classification. In: NIPS (2005)
Jain, A.K., Mao, J., Mohiuddin, K.: Artificial neural networks: a tutorial. Computer 3, 31–44 (1996)
Bache, K., Lichman, M.: UCI machine learning repository (2013). http://archive.ics.uci.edu/ml
Acknowledgments
This project has received funding from the Electronic Component Systems for European Leadership Joint Undertaking under grant agreement No 662189. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation programme and Spain, Finland, Denmark, Belgium, Netherlands, Portugal, Italy, Austria, United Kingdom, Hungary, Slovenia, Germany.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Félix, C., Soares, C., Jorge, A. (2016). Can Metalearning Be Applied to Transfer on Heterogeneous Datasets?. In: Martínez-Álvarez, F., Troncoso, A., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2016. Lecture Notes in Computer Science(), vol 9648. Springer, Cham. https://doi.org/10.1007/978-3-319-32034-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-32034-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32033-5
Online ISBN: 978-3-319-32034-2
eBook Packages: Computer ScienceComputer Science (R0)