Abstract
Ensemble methods improve the machine learning results by combining different models. However, one of the major drawbacks of these approaches is their opacity, as they do not provide results explanation and they do not allow prior knowledge integration. As the use of machine learning increases in critical areas, the explanation of classification results and the ability to introduce domain knowledge inside the learned model have become a necessity. In this paper, we present a new deep ensemble method based on argumentation that combines machine learning algorithms with a multiagent system in order to explain the results of classification and to allow injecting prior knowledge. The idea is to extract arguments from classifiers and combine the classifiers using argumentation. This allows to exploit the internal knowledge of each classifier, to provide an explanation for the decisions and facilitate integration of domain knowledge. The results demonstrate that our method effectively improves deep learning performance in addition to providing explanations and transparency of the predictions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)
Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. SIGMOD Rec. 22(2), 207–216 (1993). https://doi.org/10.1145/170036.170072
Amgoud, L., Parsons, S., Maudet, N.: Arguments, dialogue, and negotiation. In: ECAI (2000)
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl.-Based Syst. 8(6), 373–389 (1995). https://doi.org/10.1016/0950-7051(96)81920-4
Augasta, M.G., Kathirvalavakumar, T.: Reverse engineering the neural networks for rule extraction in classification problems. Neural Process. Lett. 35(2), 131–150 (2012). https://doi.org/10.1007/s11063-011-9207-8
Besnard, P., et al.: Introduction to structured argumentation. Argument Comput. 5(1), 1–4 (2014). https://doi.org/10.1080/19462166.2013.869764
Bologna, G., Hayashi, Y.: A rule extraction study on a neural network trained by deep learning. In: 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, BC, Canada, 24–29 July 2016, pp. 668–675. IEEE (2016). https://doi.org/10.1109/IJCNN.2016.7727264
Bologna, G., Hayashi, Y.: A comparison study on rule extraction from neural network ensembles, boosted shallow trees, and SVMs. Appl. Comput. Intell. Soft Comput. 2018, 1–20 (2018)
Bonzon, E., Maudet, N.: On the outcomes of multiparty persuasion. In: McBurney, P., Parsons, S., Rahwan, I. (eds.) ArgMAS 2011. LNCS (LNAI), vol. 7543, pp. 86–101. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33152-7_6
Breiman, L.: Bagging predictors. Mach. Learn. 24, 123–140 (1996)
Cocarascu, O., Toni, F.: Detecting deceptive reviews using argumentation. In: Proceedings of the 1st International Workshop on AI for Privacy and Security, PrAISe 2016, pp. 9:1–9:8. ACM, New York (2016). https://doi.org/10.1145/2970030.2970031
Craven, M., Shavlik, J.W.: Using sampling and queries to extract rules from trained neural networks. In: ICML (1994)
Craven, M.W., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Proceedings of the 8th International Conference on Neural Information Processing Systems, NIPS 1995, pp. 24–30. MIT Press, Cambridge (1995)
Dietterich, T.G.: Ensemble methods in machine learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45014-9_1
Dietterich, T.G., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. J. Artif. Intell. Res. 2, 263–286 (1995). http://dblp.uni-trier.de/db/journals/jair/jair2.html#DietterichB95
Dung, P.M.: On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artif. Intell. 77(2), 321–357 (1995)
Forgy, C.: Rete: a fast algorithm for the many pattern/many object pattern match problem. Artif. Intell. 19(1), 17–37 (1982)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm (1996)
Fu, L.: Rule generation from neural networks. IEEE Trans. Syst. Man Cybern. 24, 1114–1124 (1994)
Garcia, F.J.C., Robb, D.A., Liu, X., Laskov, A., Patrón, P., Hastie, H.F.: Explain yourself: a natural language interface for scrutable autonomous robots. CoRR arXiv:abs/1803.02088 (2018)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 93:1–93:42 (2018)
Prakken, H.: Models of persuasion dialogue. In: Simari, G., Rahwan, I. (eds.) Argumentation in Artificial Intelligence, pp. 281–300. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-98197-0_14
Hao, Z., Yao, L., Liu, B., Wang, Y.: Arguing prism: an argumentation based approach for collaborative classification in distributed environments. In: Decker, H., Lhotská, L., Link, S., Spies, M., Wagner, R.R. (eds.) DEXA 2014. LNCS, vol. 8645, pp. 34–41. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10085-2_3
Harbers, M.: Self-explaining agents in virtual training. In: EC-TEL PROLEAN (2008)
Hruschka, E.R., Ebecken, N.F.: Extracting rules from multilayer perceptrons in classification problems: a clustering-based approach. Neurocomputing 70(1), 384–397 (2006). https://doi.org/10.1016/j.neucom.2005.12.127. http://www.sciencedirect.com/science/article/pii/S0925231206000403, Neural Networks
Johnson, W.L.: Agents that learn to explain themselves. In: Proceedings of the Twelfth National Conference on Artificial Intelligence, AAAI 1994, vol. 2, pp. 1257–1263. American Association for Artificial Intelligence, Menlo Park (1994)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kontarinis, D.: Debate in a multi-agent system: multiparty argumentation protocols (2014)
van Lent, M., Fisher, W., Mancuso, M.: An explainable artificial intelligence system for small-unit tactical behavior. In: Proceedings of the 16th Conference on Innovative Applications of Artificial Intelligence, IAAI 2004, pp. 900–907. AAAI Press (2004)
Lipton, Z.C.: The mythos of model interpretability. Queue 16(3), 30:31–30:57 (2018). https://doi.org/10.1145/3236386.3241340
Lu, H., Setiono, R., Liu, H.: Effective data mining using neural networks. IEEE Trans. Knowl. Data Eng. 8(6), 957–961 (1996). https://doi.org/10.1109/69.553163
Sato, M., Tsukimoto, H.: Rule extraction from neural networks via decision tree induction. In: International Joint Conference on Neural Networks (IJCNN 2001), pp. 1870–1875 (2001)
Marchant, I., et al.: Score should be preferred to Framingham to predict cardiovascular death in French population. Eur. J. Cardiovasc. Prev. Rehabil. 16, 609–615 (2009)
Mcburney, P., Parsons, S.: Dialogue games in multi-agent systems. Informal Logic 22, 2002 (2002)
Molineaux, M., Dannenhauer, D., Aha, D.W.: Towards explainable NPCS: a relational exploration learning agent. In: AAAI Workshops (2018)
Re, M., Valentini, G.: Ensemble methods: a review, pp. 563–594 (2012)
Reed, C.: Representing dialogic argumentation. Knowl.-Based Syst. 19, 22–31 (2006)
Sato, M., Tsukimoto, H.: Rule extraction from neural networks via decision tree induction. In: IJCNN 2001, vol. 3, pp. 1870–1875 (2001)
Searle, J.: Speech Acts. An Essay in the Philosophy of Language. Cambridge University Press, Cambridge (1969)
Thimm, M., Kersting, K.: Towards argumentation-based classification. In: Logical Foundations of Uncertainty and Machine Learning, Workshop at IJCAI 2017, August 2017. http://www.mthimm.de/publications.php
Tran, S.N., d’Avila Garcez, A.: Knowledge extraction from deep belief networks for images. In: IJCAI 2013 Workshop on Neural-Symbolic Learning and Reasoning (2013)
Wardeh, M., Bench-Capon, T., Coenen, F.: Arguing from experience using multiple groups of agents. Argument Comput. 2(1), 51–76 (2011)
Wardeh, M., Coenen, F., Bench-Capon, T.: Multi-agent based classification using argumentation from experience. Auton. Agents Multi-Agent Syst. 25(3), 447–474 (2012). https://doi.org/10.1007/s10458-012-9197-6
Zilke, J.R., Loza Mencía, E., Janssen, F.: DeepRED – rule extraction from deep neural networks. In: Calders, T., Ceci, M., Malerba, D. (eds.) DS 2016. LNCS (LNAI), vol. 9956, pp. 457–473. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46307-0_29
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sendi, N., Abchiche-Mimouni, N., Zehraoui, F. (2019). Towards a Transparent Deep Ensemble Method Based on Multiagent Argumentation. In: Calvaresi, D., Najjar, A., Schumacher, M., Främling, K. (eds) Explainable, Transparent Autonomous Agents and Multi-Agent Systems. EXTRAAMAS 2019. Lecture Notes in Computer Science(), vol 11763. Springer, Cham. https://doi.org/10.1007/978-3-030-30391-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-30391-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30390-7
Online ISBN: 978-3-030-30391-4
eBook Packages: Computer ScienceComputer Science (R0)