Extension Removal in Abstract Argumentation - An Axiomatic Approach

Abstract

This paper continues the rather recent line of research on the dynamics of non-monotonic formalisms. In particular, we consider semantic changes in Dung’s abstract argumentation formalism. One of the most studied problems in this context is the so-called enforcing problem which is concerned with manipulating argumentation frameworks (AFs) such that a certain desired set of arguments becomes an extension. Here we study the inverse problem, namely the extension removal problem: is it possible – and if so how – to modify a given argumentation framework in such a way that certain undesired extensions are no longer generated? Analogously to the well known AGM paradigm we develop an axiomatic approach to the removal problem, i.e. a certain set of axioms will determine suitable manipulations. Although contraction (that is, the elimination of a particular belief) is conceptually quite different from extension removal, there are surprisingly deep connections between the two: it turns out that postulates for removal can be directly obtained as reformulations of the AGM contraction postulates. We prove a series of formal results including conditional and unconditional existence and semantical uniqueness of removal operators as well as various impossibility results – and show possible ways out.

Cite

Text

Baumann and Brewka. "Extension Removal in Abstract Argumentation - An Axiomatic Approach." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33012670

Markdown

[Baumann and Brewka. "Extension Removal in Abstract Argumentation - An Axiomatic Approach." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/baumann2019aaai-extension/) doi:10.1609/AAAI.V33I01.33012670

BibTeX

@inproceedings{baumann2019aaai-extension,
  title     = {{Extension Removal in Abstract Argumentation - An Axiomatic Approach}},
  author    = {Baumann, Ringo and Brewka, Gerhard},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {2670-2677},
  doi       = {10.1609/AAAI.V33I01.33012670},
  url       = {https://mlanthology.org/aaai/2019/baumann2019aaai-extension/}
}