Neuro-Argumentative Learning with Case-Based Reasoning
This addresses the need for more interpretable AI models in domains requiring human-aligned reasoning, though it is incremental as it builds on prior symbolic methods.
The paper tackles the problem of improving interpretability in neural networks by introducing Gradual AA-CBR, a neurosymbolic model that uses an argumentation debate structure based on cases, achieving performance comparable to neural networks while significantly outperforming existing symbolic variants.
We introduce Gradual Abstract Argumentation for Case-Based Reasoning (Gradual AA-CBR), a data-driven, neurosymbolic classification model in which the outcome is determined by an argumentation debate structure that is learned simultaneously with neural-based feature extractors. Each argument in the debate is an observed case from the training data, favouring their labelling. Cases attack or support those with opposing or agreeing labellings, with the strength of each argument and relationship learned through gradient-based methods. This argumentation debate structure provides human-aligned reasoning, improving model interpretability compared to traditional neural networks (NNs). Unlike the existing purely symbolic variant, Abstract Argumentation for Case-Based Reasoning (AA-CBR), Gradual AA-CBR is capable of multi-class classification, automatic learning of feature and data point importance, assigning uncertainty values to outcomes, using all available data points, and does not require binary features. We show that Gradual AA-CBR performs comparably to NNs whilst significantly outperforming existing AA-CBR formulations.