Heterogeneous Graph Neural Networks for Assumption-Based Argumentation

2025-11-12

AI Summary

Computing stable extensions in assumption-based argumentation (ABA) frameworks is computationally intractable. Method: This paper introduces heterogeneous graph neural networks (HGNNs) to ABA reasoning—proposing ABAGCN and ABAGAT architectures that explicitly model support, derivation, and attack relations among assumptions, rules, and conclusions. Leveraging residual heterogeneous convolutions and multi-head attention, models are trained on the ICCMA 2023 benchmark and synthetic datasets via Bayesian hyperparameter optimization. A polynomial-time extension reconstruction algorithm is further designed from model predictions. Contribution/Results: The approach achieves a node-level F1 score of 0.71—significantly outperforming existing GNN baselines. Extension reconstruction attains F1 > 0.85 on small ABA frameworks and maintains ~0.58 on large ones, balancing efficiency and accuracy. This work advances scalable, approximate reasoning for structured argumentation.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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 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. Our work opens new avenues for scalable approximate reasoning in structured argumentation.

Problem

• Approximating credulous acceptance in Assumption-Based Argumentation
• Modeling ABA frameworks via heterogeneous dependency graph representation
• Developing scalable approximate reasoning for large argumentation frameworks

Innovation

• Uses heterogeneous graph neural networks for ABA
• Proposes ABAGCN and ABAGAT with residual layers
• Develops polynomial time extension-reconstruction algorithm