Safe Neurosymbolic Learning with Differentiable Symbolic Execution
Safe Neurosymbolic Learning with Differentiable Symbolic Execution
复制标题
DOI：
10.48550/arxiv.2203.07671
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Chenxi Yang;Swarat Chaudhuri
中科院分区：
文献类型：
--
作者：
Chenxi Yang;Swarat Chaudhuri
我们研究了使用神经网络以及人类编写的符号代码的程序的最坏情况安全参数的学习问题。这种神经符号程序出现在许多安全关键领域。然而，因为它们可以使用不可微运算，所以很难使用现有的基于梯度的安全学习方法来学习它们的参数。我们解决这个问题的方法，可区分符号执行(DSE)，对程序中的控制流路径进行采样，沿着这些路径象征性地构造最坏情况的“安全损失”，并使用增强估计器的推广通过程序操作反向传播这些损失的梯度。我们在合成任务和真实世界基准的混合上对该方法进行了评估。我们的实验表明，DSE在这些任务上的表现明显优于最先进的DiffAI方法。
We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code. Such neurosymbolic programs arise in many safety-critical domains. However, because they can use nondifferentiable operations, it is hard to learn their parameters using existing gradient-based approaches to safe learning. Our approach to this problem, Differentiable Symbolic Execution (DSE), samples control flow paths in a program, symbolically constructs worst-case"safety losses"along these paths, and backpropagates the gradients of these losses through program operations using a generalization of the REINFORCE estimator. We evaluate the method on a mix of synthetic tasks and real-world benchmarks. Our experiments show that DSE significantly outperforms the state-of-the-art DiffAI method on these tasks.