Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement
This work addresses the need for explainable AI by providing a novel approach to interpret causal models, though it appears incremental as it builds on existing argumentation frameworks and causal modeling techniques.
The paper tackles the problem of explaining causal models in machine learning by introducing a method to generate argumentation frameworks from causal models, using bi-variate reinforcement as an example to create bipolar argumentative explanations, with a theoretical evaluation of their properties.
Causal models are playing an increasingly important role in machine learning, particularly in the realm of explainable AI. We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for the models' outputs. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds, which are means for characterising the relations in the causal model argumentatively. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement as an explanation mould to forge bipolar AFs as explanations for the outputs of causal models. We perform a theoretical evaluation of these argumentative explanations, examining whether they satisfy a range of desirable explanatory and argumentative properties.