Neural algorithmic reasoners are parallel processors. Teaching them sequential algorithms contradicts this nature, rendering a significant share of their computations redundant. Parallel algorithms however may exploit their full computational power, therefore requiring fewer layers to be executed. This drastically reduces training times, as we observe when comparing parallel implementations of searching, sorting and finding strongly connected components to their sequential counterparts on the CLRS framework. Additionally, parallel versions achieve (often strongly) superior predictive performance.

翻译：神经算法推理器本质上是并行处理器。用顺序算法训练它们违背了这一特性，导致其大量计算冗余。而并行算法能够充分挖掘其全部计算能力，因此需要更少的执行层。在CLRS框架上比较搜索、排序和强连通分量检测的并行实现与顺序实现时，我们发现这显著缩短了训练时间。此外，并行版本通常能获得（甚至显著）更优的预测性能。