论文标题
散射构图学习者：发现对象，属性，类似推理中的关系
The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
论文作者
论文摘要
在这项工作中，我们专注于包含Raven的渐进式矩阵（RPM）的类似推理任务。为了发现数据的组成结构，我们提出了散射组成学习者（SCL），该结构是一种序列组成神经网络的体系结构。我们的SCL在两个RPM数据集上实现了最先进的性能，平衡范围的相对相对提高了48.7％，而PGM比以前的最先进的26.4％。我们还表明，我们的模型发现对象属性（例如形状颜色，大小）及其关系（例如，进度，联合）的组成表示。我们还发现，组合物表示使SCL显着稳健，以实现测试时间域的变化，并大大提高了零弹性的概括到以前看不见的类似物。
In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), and their relationships (e.g., progression, union). We also find that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.
