Learning to Extend Program Graphs to Work-in-Progress Code

TL;DR

This paper introduces a method to adapt program graphs for incomplete code by learning to predict relationships between tokens, improving tasks like code completion and bug fixing during development.

Contribution

It proposes a novel approach to extend program graphs for work-in-progress code by learning edge relations, enabling better machine learning on incomplete code.

Findings

Relation-aware models outperform baseline on code completion.

Edge prediction improves variable misuse localization.

Fine-tuning edges enhances repair accuracy.

Abstract

Source code spends most of its time in a broken or incomplete state during software development. This presents a challenge to machine learning for code, since high-performing models typically rely on graph structured representations of programs derived from traditional program analyses. Such analyses may be undefined for broken or incomplete code. We extend the notion of program graphs to work-in-progress code by learning to predict edge relations between tokens, training on well-formed code before transferring to work-in-progress code. We consider the tasks of code completion and localizing and repairing variable misuse in a work-in-process scenario. We demonstrate that training relation-aware models with fine-tuned edges consistently leads to improved performance on both tasks.