# Generative Code Modeling with Graphs

arXiv: https://arxiv.org/abs/1805.08490 · HTML: https://mlsanity.com/paper/1805.08490/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 30 of 60)

- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations](https://mlsanity.com/paper/2202.02514/) (2022)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [A Survey on Deep Graph Generation: Methods and Applications](https://mlsanity.com/paper/2203.06714/) (2022)
- [Graph Generation with Diffusion Mixture](https://mlsanity.com/paper/2302.03596/) (2023)
- [Stealthy Backdoor Attack for Code Models](https://mlsanity.com/paper/2301.02496/) (2023)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection](https://mlsanity.com/paper/2406.06822/) (2024)
- [What do pre-trained code models know about code?](https://mlsanity.com/paper/2108.11308/) (2021)
- [StructCoder: Structure-Aware Transformer for Code Generation](https://mlsanity.com/paper/2206.05239/) (2022)
- [Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs](https://mlsanity.com/paper/2103.09499/) (2021)
- [Large Language Models of Code Fail at Completing Code with Potential Bugs](https://mlsanity.com/paper/2306.03438/) (2023)
- [SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation](https://mlsanity.com/paper/2307.01646/) (2023)
- [Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation](https://mlsanity.com/paper/2305.00909/) (2023)
- [How could Neural Networks understand Programs?](https://mlsanity.com/paper/2105.04297/) (2021)
- [A Survey on Machine Learning Techniques for Source Code Analysis](https://mlsanity.com/paper/2110.09610/) (2021)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [A Hazard Analysis Framework for Code Synthesis Large Language Models](https://mlsanity.com/paper/2207.14157/) (2022)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Guiding Language Models of Code with Global Context using Monitors](https://mlsanity.com/paper/2306.10763/) (2023)
- [Learning Structural Edits via Incremental Tree Transformations](https://mlsanity.com/paper/2101.12087/) (2021)
- [On Distribution Shift in Learning-based Bug Detectors](https://mlsanity.com/paper/2204.10049/) (2022)
- [Neural Program Generation Modulo Static Analysis](https://mlsanity.com/paper/2111.01633/) (2021)
- [Graph Diffusion Policy Optimization](https://mlsanity.com/paper/2402.16302/) (2024)
- [Flatten Graphs as Sequences: Transformers are Scalable Graph Generators](https://mlsanity.com/paper/2502.02216/) (2025)
- [CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course](https://mlsanity.com/paper/2210.14494/) (2022)
- [Syntax-Aware On-the-Fly Code Completion](https://mlsanity.com/paper/2211.04673/) (2022)
- [Discrete Graph Auto-Encoder](https://mlsanity.com/paper/2306.07735/) (2023)
- [Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models](https://mlsanity.com/paper/2403.01535/) (2024)
- [Improving Code Autocompletion with Transfer Learning](https://mlsanity.com/paper/2105.05991/) (2021)

## Abstract (arXiv)

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. The generative procedure interleaves grammar-driven expansion steps with graph augmentation and neural message passing steps. An experimental evaluation shows that our new model can generate semantically meaningful expressions, outperforming a range of strong baselines.