Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trains a neural network to predict concepts and reasons over them using rules written in answer set programming (ASP) to solve downstream tasks. Crucially, labels are only provided for the downstream prediction produced by the symbolic rules, not for the latent concepts themselves.Backpropagation through the non-differentiable ASP component requires expensive probability and gradient calculations, which has hindered scalability to more sophisticated tasks.In this paper, we address the current limitations of NeurASP by improving its computational performance through vectorization, batch processing and caching of intermediate computations during training. We compare computation speeds between the original and our new implementation of NeurASP and report speedups of multiple orders of magnitude for larger tasks. To this end, we propose a new dataset of difficult tasks involving playing cards, which we use to test the capabilities of NeurASP's enhanced learning function.

翻译：神经符号人工智能将神经网络与符号程序相结合，以生成鲁棒且可解释的预测。其中一种框架是NeurASP，它通过使用回答集编程（ASP）编写的规则来训练神经网络预测概念并对其进行推理，从而解决下游任务。关键在于，标签仅针对符号规则产生的下游预测提供，而非潜在概念本身。通过不可微的ASP组件进行反向传播需要昂贵的概率与梯度计算，这阻碍了其向更复杂任务的可扩展性。本文通过向量化、批处理及训练过程中中间计算的缓存来提升NeurASP的计算性能，以解决其当前的局限性。我们比较了原始NeurASP与新实现的运算速度，并在较大规模任务上实现了多个数量级的加速。为此，我们提出了一个包含扑克牌操作的新困难任务数据集，用于测试NeurASP增强学习功能的性能。