# Graph Neural Networks For Mapping Variables Between Programs -- Extended Version

arXiv: https://arxiv.org/abs/2307.13014 · HTML: https://mlsanity.com/paper/2307.13014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 24 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Learning to Represent Programs with Graphs](https://mlsanity.com/paper/1711.00740/) (2017)
- [Graph-based, Self-Supervised Program Repair from Diagnostic Feedback](https://mlsanity.com/paper/2005.10636/) (2020)
- [DeepBugs: A Learning Approach to Name-based Bug Detection](https://mlsanity.com/paper/1805.11683/) (2018)
- [Language-Agnostic Representation Learning of Source Code from Structure and Context](https://mlsanity.com/paper/2103.11318/) (2021)
- [Self-Supervised Bug Detection and Repair](https://mlsanity.com/paper/2105.12787/) (2021)
- [Neural Program Repair by Jointly Learning to Localize and Repair](https://mlsanity.com/paper/1904.01720/) (2019)
- [How Often Do Single-Statement Bugs Occur? The ManySStuBs4J Dataset](https://mlsanity.com/paper/1905.13334/) (2019)
- [Learning to Fix Build Errors with Graph2Diff Neural Networks](https://mlsanity.com/paper/1911.01205/) (2019)
- [Dynamic Neural Program Embedding for Program Repair](https://mlsanity.com/paper/1711.07163/) (2017)
- [Automated Clustering and Program Repair for Introductory Programming Assignments](https://mlsanity.com/paper/1603.03165/) (2016)
- [Learning Semantic Program Embeddings with Graph Interval Neural Network](https://mlsanity.com/paper/2005.09997/) (2020)
- [Structured Citation Trend Prediction Using Graph Neural Networks](https://mlsanity.com/paper/2104.02562/) (2021)
- [The Isabelle ENIGMA](https://mlsanity.com/paper/2205.01981/) (2022)
- [Verifix: Verified Repair of Programming Assignments](https://mlsanity.com/paper/2106.16199/) (2021)
- [C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments](https://mlsanity.com/paper/2206.08768/) (2022)
- [InvAASTCluster: On Applying Invariant-Based Program Clustering to Introductory Programming Assignments](https://mlsanity.com/paper/2206.14175/) (2022)
- [AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations](https://mlsanity.com/paper/2205.11023/) (2022)

## Abstract (arXiv)

Automated program analysis is a pivotal research domain in many areas of Computer Science -- Formal Methods and Artificial Intelligence, in particular. Due to the undecidability of the problem of program equivalence, comparing two programs is highly challenging. Typically, in order to compare two programs, a relation between both programs' sets of variables is required. Thus, mapping variables between two programs is useful for a panoply of tasks such as program equivalence, program analysis, program repair, and clone detection. In this work, we propose using graph neural networks (GNNs) to map the set of variables between two programs based on both programs' abstract syntax trees (ASTs). To demonstrate the strength of variable mappings, we present three use-cases of these mappings on the task of program repair to fix well-studied and recurrent bugs among novice programmers in introductory programming assignments (IPAs). Experimental results on a dataset of 4166 pairs of incorrect/correct programs show that our approach correctly maps 83% of the evaluation dataset. Moreover, our experiments show that the current state-of-the-art on program repair, greatly dependent on the programs' structure, can only repair about 72% of the incorrect programs. In contrast, our approach, which is solely based on variable mappings, can repair around 88.5%.