activity
20162024
most citedTowards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Data

2 citations · 5 across the 9 of their papers we have counts for

collaborators

11 papers

cs.AI20221 cited

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

Nico Potyka, Xiang Yin, Francesca Toni

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,…

cs.LG20222 cited

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

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. We revisit fait…

cs.LG2021

Learning Gradual Argumentation Frameworks using Genetic Algorithms

Jonathan Spieler, Nico Potyka, Steffen Staab

Gradual argumentation frameworks represent arguments and their relationships in a weighted graph. Their graphical structure and intuitive semantics makes them a potentially interes…

cs.NE2020

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

Nico Potyka

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in F…

cs.AI2020

Explainable Automated Reasoning in Law using Probabilistic Epistemic Argumentation

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. Since there is often uncertain…

cs.AI2019

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

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. Epistemic states are represented by pro…