nach oben

Erschienen in:

2021 | OriginalPaper | Buchkapitel

Post-hoc Explanation Options for XAI in Deep Learning: The Insight Centre for Data Analytics Perspective

verfasst von : Eoin M. Kenny, Eoin D. Delaney, Derek Greene, Mark T. Keane

Erschienen in: Pattern Recognition. ICPR International Workshops and Challenges

Verlag: Springer International Publishing

Einloggen

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

search-config

KI-gestützte Suche

Aus

Abstract

This paper profiles the recent research work on eXplainable AI (XAI), at the Insight Centre for Data Analytics. This work concentrates on post-hoc explanation-by-example solutions to XAI as one approach to explaining black box deep-learning systems. Three different methods of post-hoc explanation are outlined for image and time-series datasets: that is, factual, counterfactual, and semi-factual methods). The future landscape for XAI solutions is discussed.

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!

Jetzt informieren

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!

Jetzt informieren

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!

Jetzt informieren

Vorheriges Kapitel A Multi-layered Approach for Tailored Black-Box Explanations

Nächstes Kapitel Expert Level Evaluations for Explainable AI (XAI) Methods in the Medical Domain

Here, we consider factual examples as explanations; but LIME [36] gives factual information about the current test instance via feature importance scores also.

Ala-Pietilä, P.: Landline - 10/10/20: High-Level Expert Group on Artificial Intelligence. https://ec.europa.eu/digital-single-market/en/high-level-expert-group-artificial-intelligence

Ates, E., et al.: Counterfactual explanations for machine learning on multivariate time series data. arXiv:2008.10781 (2020)

Bagnall, A., et al.: The great time series classification bake off: an experimental evaluation of recently proposed algorithms. Extended Version. arXiv:1602.01711 (2016)

Byrne, R.M.J.: Counterfactuals in explainable artificial intelligence (XAI): evidence from human reasoning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) (2019)

Chen, C., et al.: This looks like that. In: NeurIPS (2020)

Dau, H.A., et al.: The UCR time series archive. arXiv:1810.07758 (2019)

Delaney, E., et al.: Instance-based counterfactual explanations for time series classification. arXiv:2009.13211 (2020)

Ford, C., et al.: Play MNIST for me! User studies on the effects of post-hoc, example-based explanations & error rates on debugging a deep learning, black-box classifier. In: IJCAI 2020 XAI Workshop (2020)

Forestier, G., et al.: Generating synthetic time series to augment sparse datasets. In: 2017 IEEE International Conference on Data Mining (2017)

10.

Frosst, N., Hinton, G.: Distilling a neural network into a soft decision tree. arXiv:1711.09784 (2017)

11.

Gilpin, L.H., et al.: Explaining explanations: an approach to evaluating interpretability of machine learning. arXiv:1806.00069 (2018)

12.

Hahn, T.: Landline - 10/10/20: Strategic Research, Innovation and Deployment Agenda. https://ai-data-robotics-partnership.eu/wp-content/uploads/2020/09/AI-Data-Robotics-Partnership-SRIDA-V3.0.pdf

13.

Karlsson, I., et al.: Explainable time series tweaking via irreversible and reversible temporal transformations. arXiv:1809.05183 (2018)

14.

Keane, M., Kenny, E.: How case-based reasoning explains neural networks: a theoretical analysis of XAI using post-hoc explanation-by-example from a survey of ANN-CBR twin-systems. In: Bach, K., Marling, C. (eds.) ICCBR 2019. LNCS (LNAI), vol. 11680, pp. 155–171. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29249-2_11CrossRef

15.

Keane, M.T., Kenny, E.M.: The twin-system approach as one generic solution for XAI. In: IJCAI 2019 XAI Workshop (2019)

16.

Keane, M.T., Smyth, B.: Good counterfactuals and where to find them: a case-based technique for generating counterfactuals for explainable AI (XAI). In: Watson, I., Weber, R. (eds.) ICCBR 2020. LNCS (LNAI), vol. 12311, pp. 163–178. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58342-2_11CrossRef

17.

Kenny, E.M., et al.: Bayesian case-exclusion and personalized explanations for sustainable dairy farming. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI 2020) (2020)

18.

Kenny, E., et al.: Predicting grass growth for sustainable dairy farming: a CBR system using Bayesian case-exclusion and post-hoc, personalized explanation-by-example (XAI). In: Bach, K., Marling, C. (eds.) ICCBR 2019. LNCS (LNAI), vol. 11680, pp. 172–187. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29249-2_12CrossRef

19.

Kenny, E.M., Keane, M.T.: On generating plausible counterfactual and semi-factual explanations for deep learning. arXiv:2009.06399 (2020)

20.

Kenny, E.M., Keane, M.T.: Twin-systems to explain artificial neural networks using case-based reasoning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019) (2019)

21.

Labaien, J., Zugasti, E., De Carlos, X.: Contrastive explanations for a deep learning model on time-series data. In: Song, M., Song, I.-Y., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DaWaK 2020. LNCS, vol. 12393, pp. 235–244. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59065-9_19CrossRef

22.

Laugel, T., et al.: Defining locality for surrogates in post-hoc interpretablity. arXiv:1806.07498 (2018)

23.

Laugel, T., et al.: The dangers of post-hoc interpretability: unjustified counterfactual explanations. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019) (2019)

24.

Leavy, S., et al.: Data, power and bias in artificial intelligence. arXiv:2008.0734 (2020)

25.

Leavy, S., Meaney, G., Wade, K., Greene, D.: Mitigating gender bias in machine learning data sets. In: Boratto, L., Faralli, S., Marras, M., Stilo, G. (eds.) BIAS 2020. CCIS, vol. 1245, pp. 12–26. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52485-2_2CrossRef

26.

Linyi, Y., et al.: Generating plausible counterfactual explanations for deep transformers in financial text classification. In: Proceedings of the 28th International Conference on Computational Linguistics (2020)

27.

Lipton, Z.C.: The mythos of model interpretability. arXiv:1606.03490 (2017)

28.

Mittelstadt, B., et al.: Explaining explanations in AI. In: Proceedings of the Conference on Fairness, Accountability, and Transparency (2019)

29.

Mueen, A., Keogh, E.: Extracting optimal performance from dynamic time warping. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)

30.

Nguyen, T.T., Le Nguyen, T., Ifrim, G.: A model-agnostic approach to quantifying the informativeness of explanation methods for time series classification. In: Lemaire, V., Malinowski, S., Bagnall, A., Guyet, T., Tavenard, R., Ifrim, G. (eds.) AALTD 2020. LNCS (LNAI), vol. 12588, pp. 77–94. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65742-0_6CrossRef

31.

Nugent, C., et al.: Gaining insight through case-based explanation. J. Intell. Inf. Syst. 32(3), 267–295 (2009). https://doi.org/10.1007/s10844-008-0069-0CrossRef

32.

O’Sullivan, B.: Landline - 10/10/20: Towards a Magna Carta for Data: Expert Opinion Piece: Engineering and Computer Science Committee. https://www.ria.ie/sites/default/files/ria_magna_carta_data.pdf

33.

Papernot, N., McDaniel, P.: Deep k-Nearest neighbors: towards confident, interpretable and robust deep learning. arXiv:1803.04765 (2018)

34.

Petitjean, F., et al.: A global averaging method for dynamic time warping, with applications to clustering. Pattern Recogn. 44, 678–693 (2011)CrossRef

35.

Prabhu, V.U., Birhane, A.: Large image datasets: a pyrrhic win for computer vision? arXiv:2006.16923 (2020)

36.

Ribeiro, M.T., et al.: “Why should I trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2016 (2016)

37.

Rudin, C.: Please stop explaining black box models for high stakes decisions. arXiv:1811.10154 (2018)

38.

Seah, J.C.Y., et al.: Chest radiographs in congestive heart failure: visualizing neural network learning. Radiology 290(2), 514–522 (2019)CrossRef

39.

Sørmo, F., et al.: Explanation in case-based reasoning-perspectives and goals. Artif. Intell. Rev. 24, 109–143 (2005). https://doi.org/10.1007/s10462-005-4607-7CrossRefMATH

40.

Wachter, S., et al.: Counterfactual explanations without opening the black box: automated decisions and the GDPR. SSRN J. 31 (2017)

41.

Horta, V.A.C., Mileo, A.: Towards explaining deep neural networks through graph analysis. In: Anderst-Kotsis, G., et al. (eds.) DEXA 2019. CCIS, vol. 1062, pp. 155–165. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-27684-3_20CrossRef

42.

Hohman, F., Kahng, M., Pienta, R., Chau, D.H.: Visual analytics in deep learning. IEEE Trans. Visual. Comput. Graphics 25, 2674–2693 (2018)CrossRef

Titel: Post-hoc Explanation Options for XAI in Deep Learning: The Insight Centre for Data Analytics Perspective
verfasst von: Eoin M. Kenny
Eoin D. Delaney
Derek Greene
Mark T. Keane
Verlag: Springer International Publishing
Buch: Pattern Recognition. ICPR International Workshops and Challenges
Print ISBN: 978-3-030-68795-3

Electronic ISBN: 978-3-030-68796-0

Copyright-Jahr: 2021
DOI: https://doi.org/10.1007/978-3-030-68796-0_2

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

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

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"