# Modular Tree Network for Source Code Representation Learning

arXiv: https://arxiv.org/abs/2104.00196 · HTML: https://mlsanity.com/paper/2104.00196/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2021.

## Built on by (most cited first, 8 of 8)

- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence](https://mlsanity.com/paper/2207.11680/) (2022)
- [On Multi-Modal Learning of Editing Source Code](https://mlsanity.com/paper/2108.06645/) (2021)
- [A Survey on Machine Learning Techniques for Source Code Analysis](https://mlsanity.com/paper/2110.09610/) (2021)
- [One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization](https://mlsanity.com/paper/2303.15822/) (2023)
- [Learning Program Representations with a Tree-Structured Transformer](https://mlsanity.com/paper/2208.08643/) (2022)
- [A Library for Representing Python Programs as Graphs for Machine Learning](https://mlsanity.com/paper/2208.07461/) (2022)

## Abstract (arXiv)

Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing models did not make full use of the unique structural information of programs. Although abstract syntax tree-based neural models can handle the tree structure in the source code, they cannot capture the richness of different types of substructure in programs. In this paper, we propose a modular tree network (MTN) which dynamically composes different neural network units into tree structures based on the input abstract syntax tree. Different from previous tree-structural neural network models, MTN can capture the semantic differences between types of ASTsubstructures. We evaluate our model on two tasks: program classification and code clone detection. Ourmodel achieves the best performance compared with state-of-the-art approaches in both tasks, showing the advantage of leveraging more elaborate structure information of the source code.