Comparison of Syntactic and Semantic Representations of Programs in Neural Embeddings
arXiv:2001.09201
Abstract
Neural approaches to program synthesis and understanding have proliferated widely in the last few years; at the same time graph based neural networks have become a promising new tool. This work aims to be the first empirical study comparing the effectiveness of natural language models and static analysis graph based models in representing programs in deep learning systems. It compares graph convolutional networks using different graph representations in the task of program embedding. It shows that the sparsity of control flow graphs and the implicit aggregation of graph convolutional networks cause these models to perform worse than naive models. Therefore it concludes that simply augmenting purely linguistic or statistical models with formal information does not perform well due to the nuanced nature of formal properties introducing more noise than structure for graph convolutional networks.
arXiv comment54 Pages, Imperial College London Masters Thesis
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Geometric deep learning: going beyond Euclidean data
- A Tutorial on Bayesian Optimization
- Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
- Adversarially Regularized Graph Autoencoder for Graph Embedding
- Dynamic Neural Program Embedding for Program Repair
- Neural Program Search: Solving Programming Tasks from Description and Examples
- Neural Guided Constraint Logic Programming for Program Synthesis
- NAPS: Natural Program Synthesis Dataset