Deep Arguing

TL;DR

Deep Arguing introduces a neurosymbolic model combining deep learning with argumentation to enhance interpretability and maintain competitive predictive performance across data modalities.

Contribution

It presents a novel end-to-end trainable framework that constructs argumentation structures for explainable classification in deep learning.

Findings

Achieves performance comparable to standard models on tabular and imaging data.

Provides faithful, case-based explanations for predictions.

Improves interpretability through structure constraints on argumentation graphs.

Abstract

Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models rely on a large number of learned parameters, tightly couple feature extraction with task objectives, and often lack explicit reasoning mechanisms, it is difficult for humans to understand how they arrive at their predictions. Understanding what representations emerge and why they arise from the training data remains an open challenge. We introduce Deep Arguing, a novel neurosymbolic approach that integrates deep learning with argumentation construction and reasoning for interpretable classification with different data modalities. In our approach deep neural networks construct an argumentation structure wherein data points support their assigned label and attack different ones. Using differentiable argumentation semantics for reasoning, the model is trained end-to-end to jointly learn feature representation and argumentative interactions. This results in argumentation structures providing faithful case-based explanations for predictions. Structure constraints over the argumentation graph guide learning, improving both interpretability and predictive performance. Experiments with tabular and imaging datasets show that Deep Arguing achieves performance competitive with standard baselines whilst offering interpretable argumentative reasoning.