# Learning to Represent Programs with Heterogeneous Graphs

arXiv: https://arxiv.org/abs/2012.04188 · HTML: https://mlsanity.com/paper/2012.04188/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [Stealthy Backdoor Attack for Code Models](https://mlsanity.com/paper/2301.02496/) (2023)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [Learning Program Representations with a Tree-Structured Transformer](https://mlsanity.com/paper/2208.08643/) (2022)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [A Library for Representing Python Programs as Graphs for Machine Learning](https://mlsanity.com/paper/2208.07461/) (2022)
- [ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding](https://mlsanity.com/paper/2504.00019/) (2025)
- [ZC3: Zero-Shot Cross-Language Code Clone Detection](https://mlsanity.com/paper/2308.13754/) (2023)
- [Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network](https://mlsanity.com/paper/2403.17351/) (2024)
- [xASTNN: Improved Code Representations for Industrial Practice](https://mlsanity.com/paper/2303.07104/) (2023)
- [Implant Global and Local Hierarchy Information to Sequence based Code Representation Models](https://mlsanity.com/paper/2303.07826/) (2023)
- [Knowledge Transfer for Pseudo-code Generation from Low Resource Programming Language](https://mlsanity.com/paper/2303.09062/) (2023)
- [Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification](https://mlsanity.com/paper/2305.04228/) (2023)
- [TCProF: Time-Complexity Prediction SSL Framework](https://mlsanity.com/paper/2502.15749/) (2025)
- [PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection](https://mlsanity.com/paper/2604.25599/) (2026)

## Abstract (arXiv)

Program source code contains complex structure information, which can be represented in structured data forms like trees or graphs. To acquire the structural information in source code, most existing researches use abstract syntax trees (AST). A group of works add additional edges to ASTs to convert source code into graphs and use graph neural networks to learn representations for program graphs. Although these works provide additional control or data flow information to ASTs for downstream tasks, they neglect an important aspect of structure information in AST itself: the different types of nodes and edges. In ASTs, different nodes contain different kinds of information like variables or control flow, and the relation between a node and all its children can also be different. To address the information of node and edge types, we bring the idea of heterogeneous graphs to learning on source code and present a new formula of building heterogeneous program graphs from ASTs with additional type information for nodes and edges. We use the ASDL grammar of programming language to define the node and edge types of program graphs. Then we use heterogeneous graph neural networks to learn on these graphs. We evaluate our approach on two tasks: code comment generation and method naming. Both tasks require reasoning on the semantics of complete code snippets. Experiment results show that our approach outperforms baseline models, including homogeneous graph-based models, showing that leveraging the type information of nodes and edges in program graphs can help in learning program semantics.