Heterogeneous Graph Neural Networks for Assumption-Based Argumentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (23) · 19117-19125
DOI: 10.1609/aaai.v40i23.38985 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Preesha Gehlot und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Assumption‐Based Argumentation (ABA) is a powerful structured argumentation formalism, but exact computation of extensions under stable semantics is intractable for large frameworks. We present the first Graph Neural Network (GNN) approach to approximate credulous acceptance in ABA. To leverage GNNs, we model ABA frameworks via a dependency graph representation encoding assumptions, claims and rules as nodes, with heterogeneous edge labels distinguishing support, derive and attack relations. We propose two GNN architectures—ABAGCN and ABAGAT—that stack residual heterogeneous convolution or attention layers, respectively, to learn node embeddings. Our models are trained on the ICCMA 2023 benchmark, augmented with synthetic ABAFs, with hyperparameters optimised via Bayesian search. Empirically, both ABAGCN and ABAGAT outperform a state‐of‐the‐art GNN baseline that we adapt from the abstract argumentation iterature, achieving a node‐level F1 score of up to 0.71 on the ICCMA instances. Finally, we develop a sound polynomial time extension‐reconstruction algorithm driven by our predictor: it reconstructs stable extensions with F1 above 0.85 on small ABAFs and maintains an F1 of about 0.58 on large frameworks. Our work opens new avenues for scalable approximate reasoning in structured argumentation.
Zitieren
APA
Gehlot, P., Rapberger, A., Russo, F., & Toni, F. (2026). Heterogeneous Graph Neural Networks for Assumption-Based Argumentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(23), 19117-19125. https://doi.org/10.1609/aaai.v40i23.38985
Vancouver
Gehlot P, Rapberger A, Russo F, Toni F. Heterogeneous Graph Neural Networks for Assumption-Based Argumentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(23):19117-19125. doi:10.1609/aaai.v40i23.38985
BibTeX
@article{Gehlot2026,
author = {Gehlot, Preesha and Rapberger, Anna and Russo, Fabrizio and Toni, Francesca},
title = {Heterogeneous Graph Neural Networks for Assumption-Based Argumentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {23},
pages = {19117--19125},
doi = {10.1609/aaai.v40i23.38985}
}
EUVIMED