Search Results for author: Nico Potyka

Found 21 papers, 6 papers with code

Contribution Functions for Quantitative Bipolar Argumentation Graphs: A Principle-based Analysis

no code implementations16 Jan 2024 Timotheus Kampik, Nico Potyka, Xiang Yin, Kristijonas Čyras, Francesca Toni

We present a principle-based analysis of contribution functions for quantitative bipolar argumentation graphs that quantify the contribution of one argument to another.

Robust Knowledge Extraction from Large Language Models using Social Choice Theory

1 code implementation22 Dec 2023 Nico Potyka, Yuqicheng Zhu, Yunjie He, Evgeny Kharlamov, Steffen Staab

Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering.

Promoting Counterfactual Robustness through Diversity

1 code implementation11 Dec 2023 Francesco Leofante, Nico Potyka

Counterfactual explanations shed light on the decisions of black-box models by explaining how an input can be altered to obtain a favourable decision from the model (e. g., when a loan application has been rejected).

counterfactual

ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]

no code implementations26 Nov 2023 Hamed Ayoobi, Nico Potyka, Francesca Toni

We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e. g. in ProtoPNet.

Image Classification

Understanding ProbLog as Probabilistic Argumentation

no code implementations30 Aug 2023 Francesca Toni, Nico Potyka, Markus Ulbricht, Pietro Totis

ProbLog is a popular probabilistic logic programming language/tool, widely used for applications requiring to deal with inherent uncertainties in structured domains.

Abstract Argumentation

Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks (Technical Report)

no code implementations25 Jul 2023 Xiang Yin, Nico Potyka, Francesca Toni

Argumentative explainable AI has been advocated by several in recent years, with an increasing interest on explaining the reasoning outcomes of Argumentation Frameworks (AFs).

Fake News Detection Recommendation Systems

Non-flat ABA is an Instance of Bipolar Argumentation

no code implementations21 May 2023 Markus Ulbricht, Nico Potyka, Anna Rapberger, Francesca Toni

Assumption-based Argumentation (ABA) is a well-known structured argumentation formalism, whereby arguments and attacks between them are drawn from rules, defeasible assumptions and their contraries.

Abstract Argumentation

SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]

1 code implementation23 Jan 2023 Hamed Ayoobi, Nico Potyka, Francesca Toni

Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging.

Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)

no code implementations21 Nov 2022 Nico Potyka, Xiang Yin, Francesca Toni

Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems.

Decision Making

Towards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Data

no code implementations19 May 2022 Nico Potyka, Xiang Yin, Francesca Toni

There is broad agreement in the literature that explanation methods should be faithful to the model that they explain, but faithfulness remains a rather vague term.

Learning Gradual Argumentation Frameworks using Genetic Algorithms

1 code implementation25 Jun 2021 Jonathan Spieler, Nico Potyka, Steffen Staab

As a first proof of concept, we propose a genetic algorithm to simultaneously learn the structure of argumentative classification models.

BIG-bench Machine Learning Interpretable Machine Learning

Pseudo-Riemannian Graph Convolutional Networks

1 code implementation6 Jun 2021 Bo Xiong, Shichao Zhu, Nico Potyka, Shirui Pan, Chuan Zhou, Steffen Staab

Empirical results demonstrate that our method outperforms Riemannian counterparts when embedding graphs of complex topologies.

Graph Reconstruction Inductive Bias +2

Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)

no code implementations10 Dec 2020 Nico Potyka

However, the connection seems helpful for combining background knowledge in form of sparse argumentation networks with dense neural networks that have been trained for complementary purposes and for learning the parameters of quantitative argumentation frameworks in an end-to-end fashion from data.

BIG-bench Machine Learning

Explainable Automated Reasoning in Law using Probabilistic Epistemic Argumentation

no code implementations12 Sep 2020 Inga Ibs, Nico Potyka

Applying automated reasoning tools for decision support and analysis in law has the potential to make court decisions more transparent and objective.

Polynomial-time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation (Technical Report)

no code implementations12 Jun 2019 Nico Potyka, Sylwia Polberg, Anthony Hunter

Probabilistic epistemic argumentation allows for reasoning about argumentation problems in a way that is well founded by probability theory.

A Tutorial for Weighted Bipolar Argumentation with Continuous Dynamical Systems and the Java Library Attractor

no code implementations30 Nov 2018 Nico Potyka

The strength of arguments can be computed based on an initial weight and the strength of attacking and supporting arguments.

A Polynomial-time Fragment of Epistemic Probabilistic Argumentation (Technical Report)

no code implementations29 Nov 2018 Nico Potyka

Probabilistic argumentation allows reasoning about argumentation problems in a way that is well-founded by probability theory.

Extending Modular Semantics for Bipolar Weighted Argumentation (Technical Report)

no code implementations19 Sep 2018 Nico Potyka

Semantically, we extend the framework with a Duality property that assures a symmetric impact of attack and support relations.

Towards Statistical Reasoning in Description Logics over Finite Domains (Full Version)

no code implementations10 Jun 2017 Rafael Peñaloza, Nico Potyka

We present a probabilistic extension of the description logic $\mathcal{ALC}$ for reasoning about statistical knowledge.

Probabilistic Reasoning in the Description Logic ALCP with the Principle of Maximum Entropy (Full Version)

no code implementations30 Jun 2016 Rafael Peñaloza, Nico Potyka

A central question for knowledge representation is how to encode and handle uncertain knowledge adequately.

Cannot find the paper you are looking for? You can Submit a new open access paper.