Research map / Graph learning / GNN architectures
Heterogeneous Graph Neural Networks for Assumption-Based Argumentation
Preesha Gehlot, Anna Rapberger, Fabrizio Russo, Francesca Toni
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use native heterogeneous GNN on dependency graph instead of ABAF-to-AF translation with AFGCNv2 | credulous acceptance prediction · ICCMA 2023 small ABAFs (<100 atoms) | node-level F1: 0.5 -> 0.72 (ABAGCN), 0.74 (ABAGAT) | Improved |
| replace GCN layers with GAT attention layers (ablation) | ABAGCN · ICCMA small ABAFs | node-level F1: 0.72 -> 0.74 | No clear effect |
| add synthetic generated ABAFs to the test set | ABAGCN and ABAGAT · ICCMA vs ICCMA+Generated test | F1 / accuracy | Mixed |
| increase ABAF size from small to large | extension reconstruction · extension-level F1 | F1: 0.85 -> 0.58 | Hurt |
| use GNN extension reconstruction instead of exact solver | ASPForABA · 15 hardest ABAFs (4,000-5,000 atoms) | runtime (s): 435s -> 192s | Improved |
Closest papers by meaning
- Systematic Relational Reasoning With Epistemic Graph Neural Networks (ICLR 2025 · similarity 0.87)
- Redefining ABA+ Semantics via Abstract Set-to-Set Attacks (AAAI 2024 · similarity 0.87)
- Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains (NeurIPS 2026 · similarity 0.86)
- Non-flat ABA Is an Instance of Bipolar Argumentation (AAAI 2024 · similarity 0.85)
- $\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
- Sound Logical Explanations for Mean Aggregation Graph Neural Networks (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
