Object-centric neuro-argumentative learning

Jacob, Abdul Rahman; Kori, Avinash; Angelis, Emanuele De; Glocker, Ben; Proietti, Maurizio; Toni, Francesca

doi:10.48550/arXiv.2506.14577

OA Location

https://arxiv.org/pdf/2506.14577

Author(s)

Jacob, Abdul Rahman

Kori, Avinash

Angelis, Emanuele De

Glocker, Ben

Proietti, Maurizio

more

Type

preprint

Abstract

Over the last decade, as we rely more on deep learning technologies to make critical decisions, concerns regarding their safety, reliability and interpretability have emerged. We introduce a novel Neural Argumentative Learning (NAL) architecture that integrates Assumption-Based Argumentation (ABA) with deep learning for image analysis. Our architecture consists of neural and symbolic components. The former segments and encodes images into facts using object-centric learning, while the latter applies ABA learning to develop ABA frameworks enabling predictions with images. Experiments on synthetic data show that the NAL architecture can be competitive with a state-of-the-art alternative.