论文标题
稀疏的关系推理与以对象为中心表示
Sparse Relational Reasoning with Object-Centric Representations
论文作者
论文摘要
我们在各种诱导的稀疏性约束下以相关神经体系结构在以对象为中心（基于插槽的）表示上进行操作时，通过关系神经体系结构学到的软室的合成性。我们发现，增加的稀疏性，尤其是在功能上，可以提高某些模型的性能，并导致更简单的关系。此外，我们观察到，当并非所有对象都完全捕获时，以对象为中心的表示可能是有害的。 CNN不太容易发生的故障模式。这些发现表明了可解释性和绩效之间的权衡，即使对于旨在解决关系任务的模型也是如此。
We investigate the composability of soft-rules learned by relational neural architectures when operating over object-centric (slot-based) representations, under a variety of sparsity-inducing constraints. We find that increasing sparsity, especially on features, improves the performance of some models and leads to simpler relations. Additionally, we observe that object-centric representations can be detrimental when not all objects are fully captured; a failure mode to which CNNs are less prone. These findings demonstrate the trade-offs between interpretability and performance, even for models designed to tackle relational tasks.
