Deep Arguing

2026-05-11

AI Summary

This work proposes a novel neuro-symbolic approach that integrates argumentation structures into deep learning frameworks to address the opacity of model decisions. By modeling support and attack relations through differentiable argumentation semantics, the method jointly optimizes predictive performance and explanation generation in an end-to-end training paradigm. Leveraging graph-structured constraints to enhance reasoning consistency, the approach achieves accuracy comparable to standard baselines on both tabular and image datasets while producing case-based argumentative explanations that faithfully reflect the underlying predictions. This significantly improves model transparency and trustworthiness without compromising performance.

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.

Problem

• interpretability
• deep learning
• reasoning
• representation understanding
• neurosymbolic

Innovation

• neurosymbolic
• argumentation
• interpretable AI
• differentiable reasoning
• end-to-end learning