Contrastive Learning-Enhanced Large Language Models for Monolith-to-Microservice Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sellami, Khaled, Saied, Mohamed Aymen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909904466345984
author Sellami, Khaled
Saied, Mohamed Aymen
author_facet Sellami, Khaled
Saied, Mohamed Aymen
contents As Monolithic applications evolve, they become increasingly difficult to maintain and improve, leading to scaling and organizational issues. The Microservices architecture, known for its modularity, flexibility and scalability, offers a solution for large-scale applications allowing them to adapt and meet the demand on an ever increasing user base. Despite its advantages, migrating from a monolithic to a microservices architecture is often costly and complex, with the decomposition step being a significant challenge. This research addresses this issue by introducing MonoEmbed, a Language Model based approach for automating the decomposition process. MonoEmbed leverages state-of-the-art Large Language Models (LLMs) and representation learning techniques to generate representation vectors for monolithic components, which are then clustered to form microservices. By evaluating various pre-trained models and applying fine-tuning techniques such as Contrastive Learning and Low Rank Adaptation (LoRA), MonoEmbed aims to optimize these representations for microservice partitioning. The evaluation of the fine-tuned models showcases that they were able to significantly improve the quality of the representation vectors when compared with pre-trained models and traditional representations. The proposed approach was benchmarked against existing decomposition methods, demonstrating superior performance in generating cohesive and balanced microservices for monolithic applications with varying scales.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04604
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contrastive Learning-Enhanced Large Language Models for Monolith-to-Microservice Decomposition
Sellami, Khaled
Saied, Mohamed Aymen
Software Engineering
D.2.11; I.2.7; I.2.2
As Monolithic applications evolve, they become increasingly difficult to maintain and improve, leading to scaling and organizational issues. The Microservices architecture, known for its modularity, flexibility and scalability, offers a solution for large-scale applications allowing them to adapt and meet the demand on an ever increasing user base. Despite its advantages, migrating from a monolithic to a microservices architecture is often costly and complex, with the decomposition step being a significant challenge. This research addresses this issue by introducing MonoEmbed, a Language Model based approach for automating the decomposition process. MonoEmbed leverages state-of-the-art Large Language Models (LLMs) and representation learning techniques to generate representation vectors for monolithic components, which are then clustered to form microservices. By evaluating various pre-trained models and applying fine-tuning techniques such as Contrastive Learning and Low Rank Adaptation (LoRA), MonoEmbed aims to optimize these representations for microservice partitioning. The evaluation of the fine-tuned models showcases that they were able to significantly improve the quality of the representation vectors when compared with pre-trained models and traditional representations. The proposed approach was benchmarked against existing decomposition methods, demonstrating superior performance in generating cohesive and balanced microservices for monolithic applications with varying scales.
title Contrastive Learning-Enhanced Large Language Models for Monolith-to-Microservice Decomposition
topic Software Engineering
D.2.11; I.2.7; I.2.2
url https://arxiv.org/abs/2502.04604