In this section
@inproceedings{Gehlot:2026:10.1609/aaai.v40i23.38985,
author = {Gehlot, P and Rapberger, A and Russo, F and Toni, F},
doi = {10.1609/aaai.v40i23.38985},
pages = {19117--19125},
publisher = {Association for the Advancement of Artificial Intelligence},
title = {Heterogeneous graph neural networks for assumption-based argumentation},
url = {http://dx.doi.org/10.1609/aaai.v40i23.38985},
year = {2026}
}
TY - CPAPER
AB - Assumption-Based Argumentation (ABA) is a powerfulstructured 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 literature, 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. Ourwork opens new avenues for scalable approximate reasoning in structured argumentation.
AU - Gehlot,P
AU - Rapberger,A
AU - Russo,F
AU - Toni,F
DO - 10.1609/aaai.v40i23.38985
EP - 19125
PB - Association for the Advancement of Artificial Intelligence
PY - 2026///
SN - 2374-3468
SP - 19117
TI - Heterogeneous graph neural networks for assumption-based argumentation
UR - http://dx.doi.org/10.1609/aaai.v40i23.38985
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: