English

Object-Centric Neuro-Argumentative Learning

Machine Learning 2025-06-18 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2506.14577,
  title  = {Object-Centric Neuro-Argumentative Learning},
  author = {Abdul Rahman Jacob and Avinash Kori and Emanuele De Angelis and Ben Glocker and Maurizio Proietti and Francesca Toni},
  journal= {arXiv preprint arXiv:2506.14577},
  year   = {2025}
}

Comments

Proceedings of Machine Learning Research, 2025 19th Conference on Neurosymbolic Learning and Reasoning

R2 v1 2026-07-01T03:21:59.531Z