论文标题
更好的关系推理表示
Better Set Representations For Relational Reasoning
论文作者
论文摘要
将关系推理纳入神经网络已大大扩大了它们的能力和范围。关系推理的一个定义特征是它在一组实体上运行，而不是标准向量表示。现有的端到端方法通常通过将潜在特征表示形式直接解释为一组来从输入中提取实体。我们表明，这些方法不尊重设置置换不变性，因此具有基本的代表性限制。为了解决此限制，我们提出了一个简单而通用的网络模块，称为SET炼油厂网络（SRN）。我们首先使用合成图像实验来证明我们的方法如何在没有明确监督的情况下有效分解对象。然后，我们将模块插入现有的关系推理模型中，并表明尊重的设定不变性会导致预测性能和鲁棒性在几个关系推理任务上的巨大提高。
Incorporating relational reasoning into neural networks has greatly expanded their capabilities and scope. One defining trait of relational reasoning is that it operates on a set of entities, as opposed to standard vector representations. Existing end-to-end approaches typically extract entities from inputs by directly interpreting the latent feature representations as a set. We show that these approaches do not respect set permutational invariance and thus have fundamental representational limitations. To resolve this limitation, we propose a simple and general network module called a Set Refiner Network (SRN). We first use synthetic image experiments to demonstrate how our approach effectively decomposes objects without explicit supervision. Then, we insert our module into existing relational reasoning models and show that respecting set invariance leads to substantial gains in prediction performance and robustness on several relational reasoning tasks.
