Argumentation for Interactive Causal Discovery

Fabrizio Russo

IJCAI 2023poster2 citations

Argumentation for Interactive Causal Discovery

Abstract

Causal reasoning reflects how humans perceive events in the world and establish relationships among them, identifying some as causes and others as effects. Causal discovery is about agreeing on these relationships and drawing them as a causal graph. Argumentation is the way humans reason systematically about an idea: the medium we use to exchange opinions, to get to know and trust each other and possibly agree on controversial matters. Developing AI which can argue with humans about causality would allow us to understand and validate the analysis of the AI and would allow the AI to bring evidence for or against humans' prior knowledge. This is the goal of this project: to develop a novel scientific paradigm of interactive causal discovery and train AI to recognise causes and effects by debating, with humans, the results of different statistical methods

Knowledge Representation and Reasoning: KRR: CausalityAI Ethics, Trust, Fairness: ETF: Trustworthy AIHumans and AI: HAI: Human-AI collaborationKnowledge Representation and Reasoning: KRR: ArgumentationMachine Learning: ML: CausalityMachine Learning: ML: Explainable/Interpretable machine learningMachine Learning: ML: Knowledge-aided learningUncertainty in AI: UAI: Causality, structural causal models and causal inferenceUncertainty in AI: UAI: Graphical models

BibTeX

@inproceedings{ijcai2023p820,
  title     = {Argumentation for Interactive Causal Discovery},
  author    = {Russo, Fabrizio},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {7091--7092},
  year      = {2023},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2023/820},
  url       = {https://doi.org/10.24963/ijcai.2023/820},
}