Abstract Diagrammatic Reasoning with Multiplex Graph Networks
Abstract Diagrammatic Reasoning with Multiplex Graph Networks
复制标题
DOI：
--
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Duo Wang;M. Jamnik;P. Lio’
中科院分区：
文献类型：
--
作者：
Duo Wang;M. Jamnik;P. Lio’
抽象推理，特别是在视觉领域，是一种复杂的人类能力，但它仍然是人工神经学习系统的一个具有挑战性的问题。在这项工作中，我们提出了MXGNet，多层图神经网络的多面板图形推理任务。MXGNet结合了三个强大的概念，即对象级表示，图神经网络和多重图，用于解决视觉推理任务。MXGNet首先为图的所有面板中的每个元素提取对象级表示，然后形成一个多层多路复用图，捕获不同图面板中对象之间的多种关系。MXGNet总结了从任务图中提取的多个图，并使用此总结从给定的候选项中选择最可能的答案。我们已经在两种类型的图形推理任务上测试了MXGNet，即图三段论和Raven Progressive Matrices（RPM）。对于欧拉图三段论任务，MXGNet达到了99.8%的最高准确率。对于PGM和RAVEN这两个用于RPM推理的综合数据集，MXGNet的性能远远优于最先进的模型。
Abstract reasoning, particularly in the visual domain, is a complex human ability, but it remains a challenging problem for artificial neural learning systems. In this work we propose MXGNet, a multilayer graph neural network for multi-panel diagrammatic reasoning tasks. MXGNet combines three powerful concepts, namely, object-level representation, graph neural networks and multiplex graphs, for solving visual reasoning tasks. MXGNet first extracts object-level representations for each element in all panels of the diagrams, and then forms a multi-layer multiplex graph capturing multiple relations between objects across different diagram panels. MXGNet summarises the multiple graphs extracted from the diagrams of the task, and uses this summarisation to pick the most probable answer from the given candidates. We have tested MXGNet on two types of diagrammatic reasoning tasks, namely Diagram Syllogisms and Raven Progressive Matrices (RPM). For an Euler Diagram Syllogism task MXGNet achieves state-of-the-art accuracy of 99.8%. For PGM and RAVEN, two comprehensive datasets for RPM reasoning, MXGNet outperforms the state-of-the-art models by a considerable margin.