Comparison of Syntactic and Semantic Representations of Programs in Neural Embeddings

01/24/2020
by   Austin P. Wright, et al.
0

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.

READ FULL TEXT
research
01/12/2020

Tensor Graph Convolutional Networks for Text Classification

Compared to sequential learning models, graph-based neural networks exhi...
research
08/19/2022

Graph Convolutional Networks from the Perspective of Sheaves and the Neural Tangent Kernel

Graph convolutional networks are a popular class of deep neural network ...
research
05/04/2018

Towards a Spectrum of Graph Convolutional Networks

We present our ongoing work on understanding the limitations of graph co...
research
07/28/2022

Using Graph Neural Networks for Program Termination

Termination analyses investigate the termination behavior of programs, i...
research
05/11/2021

Temporal graph-based approach for behavioural entity classification

Graph-based analyses have gained a lot of relevance in the past years du...
research
12/07/2021

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks

In recent years, several results in the supervised learning setting sugg...
research
06/14/2022

Exploring Representation of Horn Clauses using GNNs (technique report)

Learning program semantics from raw source code is challenging due to th...

Please sign up or login with your details

Forgot password? Click here to reset