GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts
This addresses the problem of automating program generation from intuitive specifications for software developers, representing an incremental improvement in graph recognition methods.
The paper tackles program synthesis from flow charts by proposing GRCNN, a deep neural network that recognizes graph structure from images, achieving a program synthesis accuracy of 66.4% and recognition accuracies of 94.1% for edges and 67.9% for nodes.
Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specifications. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and nodes are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.