Object-Centric Neuro-Argumentative Learning

Abdul Rahman Jacob, Avinash Kori, Emanuele De Angelis, Ben Glocker, Maurizio Proietti, Francesca Toni
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:1077-1089, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-jacob25a, title = {Object-Centric Neuro-Argumentative Learning}, author = {Jacob, Abdul Rahman and Kori, Avinash and Angelis, Emanuele De and Glocker, Ben and Proietti, Maurizio and Toni, Francesca}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {1077--1089}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/jacob25a/jacob25a.pdf}, url = {https://proceedings.mlr.press/v284/jacob25a.html}, 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.} }
Endnote
%0 Conference Paper %T Object-Centric Neuro-Argumentative Learning %A Abdul Rahman Jacob %A Avinash Kori %A Emanuele De Angelis %A Ben Glocker %A Maurizio Proietti %A Francesca Toni %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-jacob25a %I PMLR %P 1077--1089 %U https://proceedings.mlr.press/v284/jacob25a.html %V 284 %X 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.
APA
Jacob, A.R., Kori, A., Angelis, E.D., Glocker, B., Proietti, M. & Toni, F.. (2025). Object-Centric Neuro-Argumentative Learning. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:1077-1089 Available from https://proceedings.mlr.press/v284/jacob25a.html.

Related Material