Greedy ABA Learning for Case-Based Reasoning

ABA Learning is a form of logic-based learning, producing, from examples and background knowledge, symbolic representations in the form of assumption-based argumentation (ABA) frameworks that naturally encode conflicts emerging from generalising the examples as well as their resolution. ABA Learning is based on the application of transformation rules to progressively refine an initial ABA framework (the background knowledge) guided by the examples, and is typically highly nondeterministic, with the search space underpinning the choice of applied transformation rules very large. In this paper we propose a novel 'greedy' variant of ABA Learning tailored to settings where the examples and background knowledge are drawn from labelled cases as in case-based reasoning. Greedy ABA Learning applies the transformation rules in a fully deterministic way. We prove that, when the casebase is 'coherent' (i.e., where all cases with the same features have the same label), Greedy ABA Learning corresponds exactly with AA-CBR, another form of logic-based learning for case-based reasoning. Finally, we show that Greedy ABA Learning generalises beyond coherent casebases to deal with conflicts.