# Monolith to Microservices: Representing Application Software through Heterogeneous Graph Neural Network

arXiv: https://arxiv.org/abs/2112.01317 · HTML: https://mlsanity.com/paper/2112.01317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 7 of 7)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Graph Neural Network to Dilute Outliers for Refactoring Monolith Application](https://mlsanity.com/paper/2102.03827/) (2021)
- [Beyond Node Embedding: A Direct Unsupervised Edge Representation Framework for Homogeneous Networks](https://mlsanity.com/paper/1912.05140/) (2019)

## Abstract (arXiv)

Monolithic software encapsulates all functional capabilities into a single deployable unit. But managing it becomes harder as the demand for new functionalities grow. Microservice architecture is seen as an alternate as it advocates building an application through a set of loosely coupled small services wherein each service owns a single functional responsibility. But the challenges associated with the separation of functional modules, slows down the migration of a monolithic code into microservices. In this work, we propose a representation learning based solution to tackle this problem. We use a heterogeneous graph to jointly represent software artifacts (like programs and resources) and the different relationships they share (function calls, inheritance, etc.), and perform a constraint-based clustering through a novel heterogeneous graph neural network. Experimental studies show that our approach is effective on monoliths of different types.