用图神经网络近似计算复杂论证框架的可接受性，提升推理效率。
Heterogeneous Graph Neural Networks for Assumption-Based Argumentation
- 构建异构图模型，将假设、主张和规则转为带关系标签的节点
- 在ICCMA基准上达到0.71的节点级F1，优于现有基线
- 提出可快速重构稳定扩展的算法，小框架F1超0.85
假设型论证（ABA）是一种强大的结构化论证形式，但在大规模框架下，稳定语义下的扩展精确计算是难解问题。本文首次提出基于图神经网络（GNN）的方法，用于近似计算ABA中的可接受性。我们通过依赖图表示建模ABA框架，将假设、主张和规则作为节点，用异构边标签区分支持、推导和攻击关系。提出两种GNN架构——ABAGCN与ABAGAT，分别采用残差异构卷积与注意力层堆叠以学习节点嵌入。模型在ICCMA 2023基准上训练，并使用合成数据增强，通过贝叶斯优化调整超参数。实验表明，两者均优于从抽象论证文献中适配的状态最优基线，最大节点级F1达0.71。最后，我们设计了一种由预测器驱动的可靠多项式时间扩展重构算法，在小型ABA框架上实现超过0.85的F1，大型框架上保持约0.58的性能。本工作为结构化论证中的可扩展近似推理开辟了新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。