摘要

    本文提出了一种新的深度学习方法，以怀疑和轻信地接受论证，这是抽象论证中的两个关键问题，即
通常使用精确方法来解决问题，通常通过简化为SAT来解决。 我们
用随机训练机制训练图卷积神经网络，
动态平衡训练数据，并改善残余连接并实现
在过去的研究中，准确率高达97.15％，提高了30个百分点。 新的
方法应用于ICCMA 2017竞赛中的问题并达到
这种架构的最新技术水平。 此外，培训制度
用于本研究的图形在深度学习中对于图结构化NP-hard问题可能具有更广泛的应用性。

    This paper presents a new deep learning approach to sceptical and credulous acceptance of arguments, two key problems in Abstract Argumentation that
are most commonly solved using exact methods often by reduction to SAT. We
train a Graph Convolutional Neural Network with a randomised training regime,
dynamic balancing of training data, and improved residual connections and achieve
up to 97.15% accuracy improving on past studies by 30 percentage points. The new
approach is applied to problems from the ICCMA 2017 competition and achieves
a new state of the art for this type of architecture. Additionally, the training regime
used for this study has potential wider applicability in deep learning for graph structured NP-hard problems.

    http://safa2020.argumentationcompetition.org/papers/paper_5.pdf