机器学习满足Herbrand宇宙
Machine Learning Meets The Herbrand Universe
摘要:
基于CDCL的强命题(SAT)求解器的出现极大地推进了自动推理(AR)的几个领域。因此,AR的一个方向是将SAT求解器应用于表达形式,如一阶逻辑,今天存在大量的一般数学问题。这是可能的,由于Herbrand定理,它允许减少一阶问题的命题问题的实例化。核心挑战是从通常无限的Herbrand宇宙中选择正确的实例。在这项工作中,我们开发了第一个机器学习系统针对这一任务,解决其组合和不变性。特别是,我们开发了一个GNN2RNN架构的基础上不变的图神经网络(GNN),学习问题和他们的解决方案独立的符号名称(解决丰富的skolems),结合递归神经网络(RNN),建议为每个子句的实例。然后,该架构在数学问题及其基于实例的证明的语料库上进行训练,并以多种方式评估其性能。我们表明,经过训练的系统在预测正确的实例方面达到了很高的准确性,并且当与地面求解器相结合时,它能够通过受过教育的猜测来解决许多问题。据我们所知,这是第一次令人信服地使用机器学习从任意Herbrand宇宙中合成相关元素。
英文摘要:
The appearance of strong CDCL-based propositional (SAT) solvers has greatly advanced several areas of automated reasoning (AR). One of the directions in AR is thus to apply SAT solvers to expressive formalisms such as first-order logic, for which large corpora of general mathematical problems exist today. This is possible due to Herbrand's theorem, which allows reduction of first-order problems to propositional problems by instantiation. The core challenge is choosing the right instances from the typically infinite Herbrand universe. In this work, we develop the first machine learning system targeting this task, addressing its combinatorial and invariance properties. In particular, we develop a GNN2RNN architecture based on an invariant graph neural network (GNN) that learns from problems and their solutions independently of symbol names (addressing the abundance of skolems), combined with a recurrent neural network (RNN) that proposes for each clause its instantiations. The architecture is then trained on a corpus of mathematical problems and their instantiation-based proofs, and its performance is evaluated in several ways. We show that the trained system achieves high accuracy in predicting the right instances, and that it is capable of solving many problems by educated guessing when combined with a ground solver. To our knowledge, this is the first convincing use of machine learning in synthesizing relevant elements from arbitrary Herbrand universes.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。