Skip to main content

2019 | OriginalPaper | Buchkapitel

Multi-task Learning by Pareto Optimality

verfasst von : Deyan Dyankov, Salvatore Danilo Riccio, Giuseppe Di Fatta, Giuseppe Nicosia

Erschienen in: Machine Learning, Optimization, and Data Science

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Deep Neural Networks (DNNs) are often criticized because they lack the ability to learn more than one task at a time: Multitask Learning is an emerging research area whose aim is to overcome this issue. In this work, we introduce the Pareto Multitask Learning framework as a tool that can show how effectively a DNN is learning a shared representation common to a set of tasks. We also experimentally show that it is possible to extend the optimization process so that a single DNN simultaneously learns how to master two or more Atari games: using a single weight parameter vector, our network is able to obtain sub-optimal results for up to four games.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Auger, A., Bader, J., Brockhoff, D., Zitzler, E.: Hypervolume-based multiobjective optimization: theoretical foundations and practical implications. Theoret. Comput. Sci. 425, 75–103 (2012)MathSciNetCrossRef Auger, A., Bader, J., Brockhoff, D., Zitzler, E.: Hypervolume-based multiobjective optimization: theoretical foundations and practical implications. Theoret. Comput. Sci. 425, 75–103 (2012)MathSciNetCrossRef
2.
Zurück zum Zitat Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–259 (2013)CrossRef Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–259 (2013)CrossRef
3.
Zurück zum Zitat Brockman, G., et al.: Openai gym (2016) Brockman, G., et al.: Openai gym (2016)
5.
Zurück zum Zitat Conti, E., Madhavan, V., Petroski Such, F., Lehman, J., Stanley, K.O., Clune, J.: Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. In: NeurIPS 2018, Montreal, Canada (2018) Conti, E., Madhavan, V., Petroski Such, F., Lehman, J., Stanley, K.O., Clune, J.: Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. In: NeurIPS 2018, Montreal, Canada (2018)
6.
Zurück zum Zitat Fonseca, C.M., Paquete, L., López-Ibáñez, M.: An improved dimension-sweep algorithm for the hypervolume indicator. In: 2006 IEEE International Conference on Evolutionary Computation, pp. 1157–1163 (2006) Fonseca, C.M., Paquete, L., López-Ibáñez, M.: An improved dimension-sweep algorithm for the hypervolume indicator. In: 2006 IEEE International Conference on Evolutionary Computation, pp. 1157–1163 (2006)
9.
Zurück zum Zitat Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems, vol. 23, pp. 1189–1197. Curran Associates, Inc. (2010) Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems, vol. 23, pp. 1189–1197. Curran Associates, Inc. (2010)
10.
Zurück zum Zitat Maurer, A., Pontil, M., Romera-Paredes, B.: Sparse coding for multitask and transfer learning. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 343–351. PMLR, Atlanta, Georgia, USA, 17–19 June 2013. http://proceedings.mlr.press/v28/maurer13.html Maurer, A., Pontil, M., Romera-Paredes, B.: Sparse coding for multitask and transfer learning. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 343–351. PMLR, Atlanta, Georgia, USA, 17–19 June 2013. http://​proceedings.​mlr.​press/​v28/​maurer13.​html
11.
Zurück zum Zitat Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (2016) Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (2016)
13.
Zurück zum Zitat Murugesan, K., Carbonell, J.: Self-paced multitask learning with shared knowledge. IJCAI-17 (2017) Murugesan, K., Carbonell, J.: Self-paced multitask learning with shared knowledge. IJCAI-17 (2017)
14.
Zurück zum Zitat Romera-Paredes, B., Aung, H., Bianchi-Berthouze, N., Pontil, M.: Multilinear multitask learning. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 1444–1452. PMLR, Atlanta, Georgia, USA, 17–19 June 2013. http://proceedings.mlr.press/v28/romera-paredes13.html Romera-Paredes, B., Aung, H., Bianchi-Berthouze, N., Pontil, M.: Multilinear multitask learning. In: Dasgupta, S., McAllester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 28, pp. 1444–1452. PMLR, Atlanta, Georgia, USA, 17–19 June 2013. http://​proceedings.​mlr.​press/​v28/​romera-paredes13.​html
15.
Zurück zum Zitat Ruder, S.: An overview of multi-task learning in deep neural networks. CoRR (2017) Ruder, S.: An overview of multi-task learning in deep neural networks. CoRR (2017)
16.
Zurück zum Zitat Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv e-prints arXiv:1703.03864, March 2017 Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv e-prints arXiv:​1703.​03864, March 2017
18.
Zurück zum Zitat Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362, 1140–1144 (2018)MathSciNetCrossRef Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362, 1140–1144 (2018)MathSciNetCrossRef
Metadaten
Titel
Multi-task Learning by Pareto Optimality
verfasst von
Deyan Dyankov
Salvatore Danilo Riccio
Giuseppe Di Fatta
Giuseppe Nicosia
Copyright-Jahr
2019
DOI
https://doi.org/10.1007/978-3-030-37599-7_50