×
Kampik, Timotheus; Potyka, Nico; Yin, Xiang; Čyras, Kristijonas; Toni, Francesca

Contribution functions for quantitative bipolar argumentation graphs: a principle-based analysis. (English) Zbl 07905219

Int. J. Approx. Reasoning 173, Article ID 109255, 31 p. (2024).
Summary: We present a principle-based analysis of contribution functions for quantitative bipolar argumentation graphs that quantify the contribution of one argument to another. The introduced principles formalise the intuitions underlying different contribution functions as well as expectations one would have regarding the behaviour of contribution functions in general. As none of the covered contribution functions satisfies all principles, our analysis can serve as a tool that enables the selection of the most suitable function based on the requirements of a given use case.

MSC:

68T27 Logic in artificial intelligence
68T37 Reasoning under uncertainty in the context of artificial intelligence

Keywords:

quantitative argumentation; explainable AI; automated reasoning

Software:

Attractor
Cite Review PDF
Full Text: DOI arXiv

References:

[1] Sklar, E. I.; Azhar, M. Q., Explanation through argumentation, (Proceedings of the 6th International Conference on Human-Agent Interaction. Proceedings of the 6th International Conference on Human-Agent Interaction, HAI ’18, 2018, Association for Computing Machinery: Association for Computing Machinery New York, NY, USA), 277-285
[2] Čyras, K.; Rago, A.; Albini, E.; Baroni, P.; Toni, F., Argumentative XAI: a survey, (Zhou, Z.-H., 30th International Joint Conference on Artificial Intelligence, 2021, IJCAI: IJCAI Montreal), 4392-4399
[3] Vassiliades, A.; Bassiliades, N.; Patkos, T., Argumentation and explainable artificial intelligence: a survey, Knowl. Eng. Rev., 36, e5, 2021
[4] Rago, A.; Cocarascu, O.; Toni, F., Argumentation-based recommendations: fantastic explanations and how to find them, (Proceedings of the 27th International Joint Conference on Artificial Intelligence. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI’18, 2018, AAAI Press), 1949-1955
[5] Cocarascu, O.; Rago, A.; Toni, F., Extracting dialogical explanations for review aggregations with argumentative dialogical agents, (Elkind, E.; Veloso, M.; Agmon, N.; Taylor, M. E., Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems. Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS ’19, Montreal, QC, Canada, May 13-17, 2019, 2019, International Foundation for Autonomous Agents and Multiagent Systems), 1261-1269
[6] Potyka, N.; Yin, X.; Toni, F., Explaining random forests using bipolar argumentation and Markov networks, (Williams, B.; Chen, Y.; Neville, J., Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence. Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023, 2023, AAAI Press), 9453-9460
[7] Ayoobi, H.; Potyka, N.; Toni, F., Sparx: sparse argumentative explanations for neural networks, (Gal, K.; Nowé, A.; Nalepa, G. J.; Fairstein, R.; Radulescu, R., ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems. ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023. ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems. ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023, Frontiers in Artificial Intelligence and Applications, vol. 372, 2023, IOS Press), 149-156
[8] Ribeiro, M. T.; Singh, S.; Guestrin, C., “Why should i trust you?” explaining the predictions of any classifier, (Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016), 1135-1144
[9] Lundberg, S. M.; Lee, S.-I., A unified approach to interpreting model predictions, Adv. Neural Inf. Process. Syst., 30, 2017
[10] Bloniarz, A.; Talwalkar, A.; Yu, B.; Wu, C., Supervised neighborhoods for distributed nonparametric regression, (Artificial Intelligence and Statistics, 2016, PMLR), 1450-1459
[11] Plumb, G.; Molitor, D.; Talwalkar, A., Model agnostic supervised local explanations, (Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018), 2520-2529
[12] Potyka, N.; Yin, X.; Toni, F., Towards a theory of faithfulness: faithful explanations of differentiable classifiers over continuous data, arXiv preprint
[13] Čyras, K.; Kampik, T.; Weng, Q., Dispute trees as explanations in quantitative (bipolar) argumentation, (Čyras, K.; Kampik, T.; Cocarascu, O.; Rago, A., 1st International Workshop on Argumentation for EXplainable AI Co-Located with 9th International Conference on Computational Models of Argument (COMMA 2022). 1st International Workshop on Argumentation for EXplainable AI Co-Located with 9th International Conference on Computational Models of Argument (COMMA 2022), Cardiff, Wales, September 12, 2022. 1st International Workshop on Argumentation for EXplainable AI Co-Located with 9th International Conference on Computational Models of Argument (COMMA 2022). 1st International Workshop on Argumentation for EXplainable AI Co-Located with 9th International Conference on Computational Models of Argument (COMMA 2022), Cardiff, Wales, September 12, 2022, CEUR Workshop Proceedings, vol. 3209, 2022), 1-12, CEUR-WS.org
[14] Yin, X.; Potyka, N.; Toni, F., Argument attribution explanations in quantitative bipolar argumentation frameworks, (Gal, K.; Nowé, A.; Nalepa, G. J.; Fairstein, R.; Radulescu, R., ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023). ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), Frontiers in Artificial Intelligence and Applications, vol. 372, 2023, IOS Press), 2898-2905
[15] Kotonya, N.; Toni, F., Gradual argumentation evaluation for stance aggregation in automated fake news detection, (6th Workshop on Argument Mining, 2019), 156-166
[16] Li, P.; Gabbay, D.; Chi, X.; Cheng, Y., Decision making with weighted quantitative argumentation based on regression, (Logics for New-Generation AI, 2022), 59-71 · Zbl 1534.68227
[17] Chi, H.; Lu, Y.; Liao, B.; Xu, L.; Liu, Y., An optimized quantitative argumentation debate model for fraud detection in e-commerce transactions, IEEE Intell. Syst., 36, 2, 52-63, 2021
[18] Rago, A.; Toni, F.; Aurisicchio, M.; Baroni, P., Discontinuity-free decision support with quantitative argumentation debates, (Baral, C.; Delgrande, J. P.; Wolter, F., Principles of Knowledge Representation and Reasoning: Proceedings of the Fifteenth International Conference. Principles of Knowledge Representation and Reasoning: Proceedings of the Fifteenth International Conference, KR 2016, Cape Town, South Africa, April 25-29, 2016, 2016, AAAI Press), 63-73
[19] Delobelle, J.; Villata, S., Interpretability of gradual semantics in abstract argumentation, (Kern-Isberner, G.; Ognjanovic, Z., 15th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty. 15th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, LNAI, vol. 11726, 2019, Springer: Springer Belgrade), 27-38 · Zbl 1535.68331
[20] Shapley, L. S., Notes on the N-Person Game, 1951, Rand Corporation
[21] Amgoud, L.; Ben-Naim, J., Evaluation of arguments in weighted bipolar graphs, Int. J. Approx. Reason., 99, 39-55, 2018 · Zbl 1446.68144
[22] Potyka, N., Extending modular semantics for bipolar weighted argumentation, (Agmon, N.; Elkind, E.; Taylor, M. E.; Veloso, M., 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019, IFAAMAS: IFAAMAS Montreal), 1722-1730
[23] Baroni, P.; Rago, A.; Toni, F., From fine-grained properties to broad principles for gradual argumentation: a principled spectrum, Int. J. Approx. Reason., 105, 252-286, 2019 · Zbl 1452.68200
[24] Baroni, P.; Romano, M.; Toni, F.; Aurisicchio, M.; Bertanza, G., Automatic evaluation of design alternatives with quantitative argumentation, Argument Comput., 6, 1, 24-49, 2015
[25] Potyka, N., Continuous dynamical systems for weighted bipolar argumentation, (Thielscher, M.; Toni, F.; Wolter, F., Principles of Knowledge Representation and Reasoning: Proceedings of the Sixteenth International Conference. Principles of Knowledge Representation and Reasoning: Proceedings of the Sixteenth International Conference, KR 2018, Tempe, Arizona, 30 October - 2 November 2018, 2018, AAAI Press), 148-157
[26] Potyka, N., Interpreting neural networks as quantitative argumentation frameworks, (Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021, AAAI Press), 6463-6470
[27] Mossakowski, T.; Neuhaus, F., Modular semantics and characteristics for bipolar weighted argumentation graphs, arXiv preprint
[28] Potyka, N., Continuous dynamical systems for weighted bipolar argumentation, (Thielscher, Michael; Toni, F.; Wolte, F., Principles of Knowledge Representation and Reasoning: 16th International Conference, 2018), 148-157
[29] Shapley, L., A value for n-person games, Ann. Math. Stud., 28, 307-318, 1953 · Zbl 0050.14404
[30] Davies, A.; Veličković, P.; Buesing, L.; Blackwell, S.; Zheng, D.; Tomašev, N.; Tanburn, R.; Battaglia, P.; Blundell, C.; Juhász, A.; Lackenby, M.; Williamson, G.; Hassabis, D.; Kohli, P., Advancing mathematics by guiding human intuition with AI, Nature, 600, 7887, 70-74, 2021 · Zbl 1505.57001
[31] Verheij, B., Two approaches to dialectical argumentation: admissible sets and argumentation stages, (Proc. NAIC 96, 1996), 357-368
[32] Kampik, T.; Čyras, K.; Alarcón, J. Ruiz, Change in quantitative bipolar argumentation: sufficient, necessary, and counterfactual explanations, Int. J. Approx. Reason., Article 109066 pp., 2023 · Zbl 07879242
[33] Potyka, N., A tutorial for weighted bipolar argumentation with continuous dynamical systems and the Java library attractor, (International Workshop on Non-Monotonic Reasoning (NMR), 2018)
[34] Amgoud, L.; Ben-Naim, J.; Vesic, S., Measuring the intensity of attacks in argumentation graphs with Shapley value, (Sierra, C., Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017, 2017), 63-69, ijcai.org
[35] Yin, X.; Potyka, N.; Toni, F., Explaining arguments’ strength: unveiling the role of attacks and supports, (International Joint Conference on Artificial Intelligence (IJCAI), 2024), in press
[36] Rago, A.; Cocarascu, O.; Bechlivanidis, C.; Lagnado, D.; Toni, F., Argumentative explanations for interactive recommendations, Artif. Intell., 296, Article 103506 pp., 2021 · Zbl 1519.68269
[37] Amgoud, L.; Doder, D.; Vesic, S., Evaluation of argument strength in attack graphs: foundations and semantics, Artif. Intell., 302, Article 103607 pp., 2022 · Zbl 1478.68339
[38] Himeur, A.; Yun, B.; Bisquert, P.; Croitoru, M., Assessing the impact of agents in weighted bipolar argumentation frameworks, (Bramer, M.; Ellis, R., Artificial Intelligence XXXVIII - 41st SGAI International Conference on Artificial Intelligence, Proceedings. Artificial Intelligence XXXVIII - 41st SGAI International Conference on Artificial Intelligence, Proceedings, AI 2021, Cambridge, UK, December 14-16, 2021. Artificial Intelligence XXXVIII - 41st SGAI International Conference on Artificial Intelligence, Proceedings. Artificial Intelligence XXXVIII - 41st SGAI International Conference on Artificial Intelligence, Proceedings, AI 2021, Cambridge, UK, December 14-16, 2021, Lecture Notes in Computer Science, vol. 13101, 2021, Springer), 75-88
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.