Publications
44 results found
Potyka N, Yin X, Toni F, 2023, Explaining random forests using bipolar argumentation and Markov networks, AAAI 23, Pages: 9458-9460, ISSN: 2159-5399
Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. We show that their decision process can be naturally represented as an argumentation problem, which allows creating global explanations via argumentative reasoning. We generalize sufficientand necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the explanation problems is high, we present an efficient approximation algorithm with probabilistic approximation guarantees.
Potyka N, 2021, Interpreting Neural Networks as Quantitative Argumentation Frameworks, Thirty-Fifth AAAI Conference on Artificial Intelligence, Publisher: AAAI Press, Pages: 6463-6470
Potyka N, 2021, From Probabilistic Programming to Probabilistic Argumentation, Publisher: CEUR-WS.org
Potyka N, 2021, Generalizing Complete Semantics to Bipolar Argumentation Frameworks, Publisher: Springer, Pages: 130-143
Potyka N, 2020, Abstract Argumentation with Markov Networks, 24th European Conference on Artificial Intelligence, Publisher: IOS Press, Pages: 865-872
Potyka N, 2020, Bipolar Abstract Argumentation with Dual Attacks and Supports, Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020), Pages: 677-686
Potyka N, 2020, Foundations for Solving Classification Problems with Quantitative Abstract Argumentation, Publisher: CEUR-WS.org
Potyka N, 2019, Extending Modular Semantics for Bipolar Weighted Argumentation, Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS ’19), Publisher: International Foundation for Autonomous Agents and Multiagent Systems, Pages: 1722-1730
Potyka N, 2019, A polynomial-time fragment of epistemic probabilistic argumentation, International Journal of Approximate Reasoning, Vol: 115, Pages: 265-289, ISSN: 0888-613X
Hunter A, Polberg S, Potyka N, 2019, Delegated updates in epistemic graphs for opponent modelling, Int. J. Approx. Reason., Vol: 113, Pages: 207-244
Potyka N, 2019, A Polynomial-time Fragment of Epistemic Probabilistic Argumentation, Publisher: International Foundation for Autonomous Agents and Multiagent Systems, Pages: 2165-2167
Potyka N, 2019, Open-Mindedness of Gradual Argumentation Semantics, Publisher: Springer, Pages: 236-249
Potyka N, 2019, Extending Modular Semantics for Bipolar Weighted Argumentation (Extended Abstract), Publisher: Springer, Pages: 273-276
Potyka N, Polberg S, Hunter A, 2019, Polynomial-Time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation, Publisher: Springer, Pages: 74-86
Potyka N, 2018, Continuous Dynamical Systems for Weighted Bipolar Argumentation, Proceedings of the Sixteenth International Conference on Principles of Knowledge Representation and Reasoning (KR 2018), Publisher: AAAI Press, Pages: 148-157
Potyka N, 2018, Measuring Disagreement among Knowledge Bases, Publisher: CEUR-WS.org
Potyka N, 2018, Measuring Disagreement Among Knowledge Bases, Publisher: Springer, Pages: 212-227
Hunter A, Polberg S, Potyka N, 2018, Updating Belief in Arguments in Epistemic Graphs, Publisher: AAAI Press, Pages: 138-147
Potyka N, Thimm M, 2017, Inconsistency-tolerant reasoning over linear probabilistic knowledge bases, International Journal of Approximate Reasoning, Vol: 88, Pages: 209-236, ISSN: 0888-613X
naloza RP, Potyka N, 2017, Towards Statistical Reasoning in Description Logics over Finite Domains, Publisher: Springer, Pages: 280-294
Hunter A, Potyka N, 2017, Updating Probabilistic Epistemic States in Persuasion Dialogues, Publisher: Springer, Pages: 46-56
Beierle C, Finthammer M, Potyka N, et al., 2017, A Framework for Versatile Knowledge and Belief Management Operations in a Probabilistic Conditional Logic, FLAP, Vol: 4
Potyka N, Acar E, Thimm M, et al., 2016, Group Decision Making via Probabilistic Belief Merging, The Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2016), Publisher: IJCAI/AAAI Press, Pages: 3623-3629
naloza RP, Potyka N, 2016, Probabilistic Reasoning in the Description Logic ALCP with the Principle of Maximum Entropy, Publisher: Springer, Pages: 246-259
Potyka N, 2016, Relationships Between Semantics for Relational Probabilistic Conditional Logics, Publisher: College Publications, Pages: 332-347
Potyka N, Gómez-Ramírez D, Kühnberger K-U, 2016, Towards a Computational Framework for Function-Driven Concept Invention, Publisher: Springer, Pages: 212-222
Potyka N, Mittermeier E, Marenke D, 2016, An overview of algorithmic approaches to compute optimum entropy distributions in the expert system shell MECore (extended version), J. Appl. Log., Vol: 19, Pages: 71-86
Potyka N, 2016, Solving Reasoning Problems for Probabilistic Conditional Logics with Consistent and Inconsistent Information
Potyka N, Thimm M, 2015, Probabilistic Reasoning with Inconsistent Beliefs Using Inconsistency Measures, The Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), Publisher: AAAI Press, Pages: 3156-3163
Potyka N, Beierle C, Kern-Isberner G, 2015, A concept for the evolution of relational probabilistic belief states and the computation of their changes under optimum entropy semantics, J. Appl. Log., Vol: 13, Pages: 414-440
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.