Skip to main content
SpringerLink
Log in

Explainable Machine Learning via Argumentation

  • Conference paper
  • First Online:
Explainable Artificial Intelligence (xAI 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1903))

Included in the following conference series:

Abstract

This paper presents a general Explainable Machine Learning framework and methodology based on Argumentation (ArgEML). The flexible reasoning form of argumentation in the face of unknown and incomplete information together with the direct link of argumentation to justification and explanation enables the development of a natural form of explainable machine learning. In this form of learning the explanations are useful not only for supporting the final predictions but also play a significant role in the learning process itself. The paper defines the basic theoretical notions of ArgEML together with its main machine learning operators and method of application. It describes how such an argumentation-based approach can give a flexible way for learning that recognizes difficult cases (with respect to the current available training data) and separates these cases out not as definite predictive cases but as cases where it is more appropriate to explainably analyze the alternative predictions. Using the argumentation-based explanations we can partition the problem space into groups characterized by the basic argumentative tension between arguments for and against the alternatives. The paper presents a first evaluation of the approach by applying the ArgEML learning methodology both on artificial and on real-life datasets.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    We will use a Logic Programming rule notation for the arguments to facilitate the exposition of the realization of the ArgEML framework in the next sections of the paper.

  2. 2.

    https://www.swi-prolog.org/.

  3. 3.

    https://jpl7.org/.

  4. 4.

    http://gorgiasb.tuc.gr/.

  5. 5.

    https://cran.r-project.org/web/packages/inTrees/index.html.

  6. 6.

    All datasets presented here are available via request from the authors.

  7. 7.

    https://archive.ics.uci.edu/ml/datasets/iris.

  8. 8.

    A measure of each rule’s relative importance in predicting the correct class.

  9. 9.

    st:Stenosis (%ECST). ECST: European Carotid Surgery Trial. Lngsm40: Log(GSM + 40). GSM: Grey Scale Median. Cubrar: (Plaque Area)1/3 in mm2. Dwa1: DWAs (#of Yes cases).DWA: Discrete White Areas. Ctiastr1: History of contr. TIAs and/or Stroke (#of Yes cases). Target: {asympt, stroke}.

References

  1. Longo, L.: Argumentation for knowledge representation, conflict resolution, defeasible inference and its integration with machine learning. In: Holzinger, A. (ed.) Machine Learning for Health Informatics. LNCS, vol. 9605, pp. 183–208. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50478-0_9

    Chapter  Google Scholar 

  2. Kakas, A., Michael, L.: Abduction and argumentation for explainable machine learning: a position survey. arXiv (2020). http://arxiv.org/abs/2010.12896

  3. Vassiliades, A., Bassiliades, N., Patkos, T.: Argumentation and explainable artificial intelligence: a survey. Knowl. Eng. Rev. 36, e5 (2021). https://doi.org/10.1017/S0269888921000011

    Article  Google Scholar 

  4. Možina, M., Žabkar, J., Bratko, I.: Argument based machine learning. Artif. Intell. 171(10–15), 922–937 (2007). https://doi.org/10.1016/j.artint.2007.04.007

    Article  MathSciNet  MATH  Google Scholar 

  5. Žabkar, J., Možina, M., Videčnik, J., Bratko, I.: Argument based machine learning in a medical domain. Front. Artif. Intell. Appl. 144, 59–70 (2006)

    Google Scholar 

  6. Možina, M., Giuliano, C., Bratko, I.: Argument based machine learning from examples and text (2009). https://doi.org/10.1109/ACIIDS.2009.60

  7. Groza, A., Toderean, L., Muntean, G.A., Nicoara, S.D.: Agents that argue and explain classifications of retinal conditions. J. Med. Biol. Eng. 41(5), 730–741 (2021). https://doi.org/10.1007/s40846-021-00647-7

    Article  Google Scholar 

  8. Ontañón, S., Plaza, E.: Coordinated inductive learning using argumentation-based communication. Auton. Agent. Multi. Agent. Syst. 29(2), 266–304 (2015). https://doi.org/10.1007/s10458-014-9256-2

    Article  Google Scholar 

  9. Niskanen, A., Wallner, J.P., Järvisalo, M.: Synthesizing argumentation frameworks from examples. J. Artif. Intell. Res. 66(503), 554 (2019). https://doi.org/10.1613/jair.1.11758

    Article  MathSciNet  MATH  Google Scholar 

  10. Yras, K.Č., Satoh, K., Toni, F.: Abstract argumentation for case-based reasoning. In: Proceedings of the International Conference on Knowledge Represention and Reasoning, no. Kr, pp. 549–552 (2016)

    Google Scholar 

  11. Ayoobi, H., Cao, M., Verbrugge, R., Verheij, B.: Argumentation-based online incremental learning. IEEE Trans. Autom. Sci. Eng. 19(4), 3419–3433 (2022). https://doi.org/10.1109/TASE.2021.3120837

    Article  Google Scholar 

  12. Potyka, N., Bazo, M., Spieler, J., Staab, S.: Learning gradual argumentation frameworks using meta-heuristics. In: CEUR Workshop Proceedings, vol. 3208 (2022)

    Google Scholar 

  13. Dimopoulos, Y., Kakas, A.: Learning non-monotonic logic programs: learning exceptions. In: Lavrac, N., Wrobel, S. (eds.) ECML 1995. LNCS, vol. 912, pp. 122–137. Springer, Heidelberg (1995). https://doi.org/10.1007/3-540-59286-5_53

    Chapter  Google Scholar 

  14. Wardeh, M., Coenen, F., Capon, T.B.: PISA: a framework for multiagent classification using argumentation. Data Knowl. Eng. 75, 34–57 (2012). https://doi.org/10.1016/j.datak.2012.03.001

    Article  Google Scholar 

  15. Michael, L.: Cognitive reasoning and learning mechanisms. In: CEUR Workshop Proceedings, vol. 1895 (2017)

    Google Scholar 

  16. Prentzas, N., Nicolaides, A., Kyriacou, E., Kakas, A., Pattichis, C.: Integrating machine learning with symbolic reasoning to build an explainable AI model for stroke prediction. In: Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019, pp. 817–821 (2019). https://doi.org/10.1109/BIBE.2019.00152

  17. Maurizio, P., Toni, F.: Learning assumption-based argumentation frameworks (2022). http://hdl.handle.net/10044/1/98940

  18. Carstens, L., Toni, F.: Improving out-of-domain sentiment polarity classification using argumentation (2016). https://doi.org/10.1109/ICDMW.2015.185

  19. Loizos, M.: Machine coaching (2019). https://api.semanticscholar.org/CorpusID:236161635

  20. Potyka, N.: Interpreting neural networks as quantitative argumentation frameworks. In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, vol. 7 (2021). https://doi.org/10.1609/aaai.v35i7.16801

  21. Riveret, R., Tran, S., Garcez, A.D.A.: Neural-symbolic probabilistic argumentation machines. In: 17th International Conference on Principles of Knowledge Representation and Reasoning, KR 2020, vol. 2 (2020). https://doi.org/10.24963/kr.2020/90

  22. Tsamoura, E., Hospedales, T., Michael, L.: Neural-symbolic integration: a compositional perspective. In: 35th AAAI Conference on Artificial Intelligence, AAAI 2021, vol. 6A (2021). https://doi.org/10.1609/aaai.v35i6.16639

  23. Sendi, N., Abchiche-Mimouni, N., Zehraoui, F.: A new transparent ensemble method based on deep learning. Procedia Comput. Sci. 159, 271–280 (2019). https://doi.org/10.1016/j.procs.2019.09.182

    Article  Google Scholar 

  24. Dejl, A., et al.: Argflow: a toolkit for deep argumentative explanations for neural networks. In: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, vol. 3 (2021)

    Google Scholar 

  25. Bench-Capon, T.J.M., Dunne, P.E.: Argumentation in artificial intelligence. Artif. Intell. 171(10–15), 619–641 (2007). https://doi.org/10.1016/j.artint.2007.05.001

    Article  MathSciNet  MATH  Google Scholar 

  26. Rahwan, I., Simari, G.R.: Argumentation in artificial intelligence (2009)

    Google Scholar 

  27. Spanoudakis, N.I., Kakas, A.C., Moraitis, P.: Applications of argumentation: the SoDA methodology. In: Frontiers in artificial intelligence and applications, vol. 285 (2016). https://doi.org/10.3233/978-1-61499-672-9-1722

  28. Longo, L., Rizzo, L., Dondio, P.: Examining the modelling capabilities of defeasible argumentation and non-monotonic fuzzy reasoning. Knowl.-Based Syst. 211, 106514 (2021). https://doi.org/10.1016/j.knosys.2020.106514

    Article  Google Scholar 

  29. Kakas, A., Moraïtis, P.: Argumentation based decision making for autonomous agents. In: Proceedings of the International Conference on Autonomous Agents, vol. 2 (2003). https://doi.org/10.1145/860575.860717

  30. Dietz, E., Kakas, A., Loizos, M.: Computational argumentation & cognitive AI. In: Chetouani, M., Dignum, V., Lukowicz, P., Sierra, C. (eds.) ACAI 2021. LNCS, vol. 13500, pp. 363–388. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-24349-3_19

    Chapter  Google Scholar 

  31. Kakas, A.C., Moraitis, P., Spanoudakis, N.I.: GORGIAS: applying argumentation. Argument Comput. 10(1), 55–81 (2019). https://doi.org/10.3233/AAC-181006

    Article  Google Scholar 

  32. Spanoudakis, N.I., Kakas, A.C., Koumi, A.: Application level explanations for argumentation-based decision making. In: CEUR Workshop Proceedings, vol. 3209 (2022)

    Google Scholar 

  33. 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). https://doi.org/10.1016/0004-3702(94)00041-X

    Article  MathSciNet  MATH  Google Scholar 

  34. Cyras, K., Rago, A., Albini, E., Baroni, P., Toni, F.: Argumentative XAI: a survey (2021). https://doi.org/10.24963/ijcai.2021/600

  35. Sklar, E.I., Azhar, M.Q.: Explanation through argumentation (2018). https://doi.org/10.1145/3284432.3284470

  36. Rago, A., Cocarascu, O., Toni, F.: Argumentation-based recommendations: fantastic explanations and how to find them. In: IJCAI International Joint Conference on Artificial Intelligence, vol. 2018-July (2018). https://doi.org/10.24963/ijcai.2018/269

  37. Miller, T.: Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 267, 1–38 (2019). https://doi.org/10.1016/j.artint.2018.07.007

    Article  MathSciNet  MATH  Google Scholar 

  38. Deng, H.: Interpreting tree ensembles with inTrees. Int. J. Data Sci. Anal. 7(4), 277–287 (2018). https://doi.org/10.1007/s41060-018-0144-8

    Article  Google Scholar 

  39. Letham, B., Rudin, C., McCormick, T.H., Madigan, D.: Interpretable classifiers using rules and bayesian analysis: Building a better stroke prediction model. Ann. Appl. Stat. 9(3), 1350–1371 (2015). https://doi.org/10.1214/15-AOAS848

    Article  MathSciNet  MATH  Google Scholar 

  40. Holte, R.C.: Very simple classification rules perform well on most commonly used datasets. Mach. Learn. 11(1), 63–90 (1993). https://doi.org/10.1023/A:1022631118932

    Article  MATH  Google Scholar 

  41. Nicolaides, A.N., et al.: Asymptomatic internal carotid artery stenosis and cerebrovascular risk stratification. J. Vasc. Surg. 52(6), 1486–1496 (2010). https://doi.org/10.1016/j.jvs.2010.07.021

    Article  Google Scholar 

  42. Yáñez, C.S.: Mercier and Sperber’s argumentative theory of reasoning: from the psychology of reasoning to argumentation studies. Inform. Log. 32(1), 132–159 (2012). https://doi.org/10.22329/il.v32i1.3536

    Article  Google Scholar 

  43. Čyras, K., et al.: Machine reasoning explainability. arXiv (2020)

    Google Scholar 

  44. Ribeiro, M.T., Singh, S., Guestrin, C.: ‘Why should i trust you?’ Explaining the predictions of any classifier. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 13–17-Augu, pp. 1135–1144 (2016). https://doi.org/10.1145/2939672.2939778

  45. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 2017-Decem, pp. 4766–4775 (2017)

    Google Scholar 

  46. Setzu, M., Guidotti, R., Monreale, A., Turini, F., Pedreschi, D., Giannotti, F.: GLocalX - from local to global explanations of black box AI models. Artif. Intell. 294, 103457 (2021). https://doi.org/10.1016/j.artint.2021.103457

    Article  MathSciNet  Google Scholar 

  47. Dietz, E., Kakas, A., Michael, L.: Argumentation: a calculus for human-centric AI. Front. Artif. Intell. 5, 955579 (2022). https://doi.org/10.3389/frai.2022.955579

    Article  Google Scholar 

  48. Prentzas, N., Gavrielidou, A., Neophytou, M., Kakas, A.: Argumentation-based explainable machine learning (ArgEML): a real-life use case on gynecological cancer. In: CEUR Workshop Proceedings, vol. 3208 (2022)

    Google Scholar 

  49. Nicolaou, A., Loizou, C.P., Pantzaris, M., Kakas, A., Pattichis, C.S.: Rule extraction in the assessment of brain mri lesions in multiple sclerosis: preliminary findings. In: Tsapatsoulis, N., Panayides, A., Theocharides, T., Lanitis, A., Pattichis, C., Vento, M. (eds.) CAIP 2021. LNCS (LNAI and LNB), vol. 13052, pp. 277–286. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-89128-2_27

    Chapter  Google Scholar 

  50. Albini, E., Lertvittayakumjorn, P., Rago, A., Toni, F.: DAX: deep argumentative explanation for neural networks (2020)

    Google Scholar 

Download references

Acknowledgements

Part of this work was undertaken under the University of Cyprus internal project, Integrated Explainable AI (IXAI) for Medical Decision Support, ARGEML 8037P-22046. This study is also partly funded by the project ‘Atherorisk’ “Identification of unstable carotid plaques associated with symptoms using ultrasonic image analysis and plaque motion analysis”, code: Excellence/0421/0292, funded by the Research and In-novation Foundation, the Republic of Cyprus.

Author information

Authors and Affiliations

  1. University of Cyprus, 1 Panepistimiou Avenue, 2109, Nicosia, Cyprus

    Nicoletta Prentzas, Constantinos Pattichis & Antonis Kakas

  2. CYENS Centre of Excellence, 23 Dimarchou Lellou Demetriadi, 1016, Nicosia, Cyprus

    Constantinos Pattichis

Authors
  1. Nicoletta Prentzas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Constantinos Pattichis
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Antonis Kakas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nicoletta Prentzas .

Editor information

Editors and Affiliations

  1. Technological University Dublin, Dublin, Ireland

    Luca Longo

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Prentzas, N., Pattichis, C., Kakas, A. (2023). Explainable Machine Learning via Argumentation. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1903. Springer, Cham. https://doi.org/10.1007/978-3-031-44070-0_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-44070-0_19

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-44069-4

  • Online ISBN: 978-3-031-44070-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation