Can a generic (Python) program be executed statement-by-statement by neural
networks composed according to the source code? We formulate the Abstract
Neural Execution Problem and introduce Neural Interpretation, the first neural
model that abstractly executes generic source code, where every variable has a
vector encoding, and every function executes a neural network. Neural
Interpretation is a model of computers with a compiler architecture, which can
assemble neural layers ''programmed'' by partial source code. Neural
Interpretation can be trained with flexible learning objectives. We demonstrate
white-box execution without concrete inputs for variable misuse localization
and repair.

介绍了一种新的神经模型 Neural Interpretation，能够抽象地执行具有一定泛化性的 Python 代码，它的变量和函数都有着相应的神经网络，通过一定的学习目标进行训练使得可以准确地定位和修复变量误用。

通用源代码的神经解释

Neural Interpretation of Generic Source Code

Graph neural networks (GNNs) have found application for learning in the space
of algorithms. However, the algorithms chosen by existing research (sorting,
Breadth-First search, shortest path finding, etc.) usually align perfectly with
a standard GNN architecture. This report describes how neural execution is
applied to a complex algorithm, such as finding maximum bipartite matching by
reducing it to a flow problem and using Ford-Fulkerson to find the maximum
flow. This is achieved via neural execution based only on features generated
from a single GNN. The evaluation shows strongly generalising results with the
network achieving optimal matching almost 100% of the time.

本文介绍了如何利用单个图神经网络的特征，通过神经执行将复杂算法（如最大二分匹配）转化为流量问题，并使用 Ford-Fulkerson 算法实现最大流问题的求解，该方法取得了 100% 的理想匹配效果。