Neuro-Argumentative Learning with Case-Based Reasoning

TL;DR

This paper presents Gradual AA-CBR, a neurosymbolic classification model that combines argumentation debate structures with neural feature extractors, enhancing interpretability and performance in multi-class classification tasks.

Contribution

It introduces Gradual AA-CBR, a novel neurosymbolic model capable of multi-class classification, automatic importance learning, and uncertainty estimation, improving upon existing symbolic argumentation methods.

Findings

Performs comparably to neural networks in classification accuracy.

Significantly outperforms existing AA-CBR models.

Provides human-aligned reasoning with enhanced interpretability.

Abstract

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.