论文标题
高维空间中的可区分归纳逻辑编程
Differentiable Inductive Logic Programming in High-Dimensional Space
论文作者
论文摘要
通过符号归纳逻辑编程（ILP）综合大型逻辑程序通常需要中间定义。但是，用强化谓词混乱假设空间通常会降低性能。相比之下，梯度下降提供了一种在此类高维空间内找到解决方案的有效方法。到目前为止，神经符号ILP方法尚未完全利用这一点。我们提出了扩展ΔILP方法以大规模谓词发明的感应合成，从而使我们能够利用高维梯度下降的功效。我们表明，大规模谓词发明通过梯度下降有益于可区分的归纳合成，并允许人们学习解决现有神经符号ILP系统功能之外的任务的解决方案。此外，我们实现了这些结果，而无需指定语言偏见中解决方案的精确结构。
Synthesizing large logic programs through symbolic Inductive Logic Programming (ILP) typically requires intermediate definitions. However, cluttering the hypothesis space with intensional predicates typically degrades performance. In contrast, gradient descent provides an efficient way to find solutions within such high-dimensional spaces. Neuro-symbolic ILP approaches have not fully exploited this so far. We propose extending the δILP approach to inductive synthesis with large-scale predicate invention, thus allowing us to exploit the efficacy of high-dimensional gradient descent. We show that large-scale predicate invention benefits differentiable inductive synthesis through gradient descent and allows one to learn solutions for tasks beyond the capabilities of existing neuro-symbolic ILP systems. Furthermore, we achieve these results without specifying the precise structure of the solution within the language bias.
