@INPROCEEDINGS{Trabelsi24-ICSA-MAGNET,
   AUTHOR       = {Imen Trabelsi and Naouel Moha and Yann-Ga�l Gu�h�neuc and 
      Lucas Geffard},
   BOOKTITLE    = {Proceedings of the 21<sup>st</sup> International Conference on Software Architecture (ICSA)},
   TITLE        = {MAGNET: Method-based Approach using Graph Neural Network 
      for Microservices Identification},
   YEAR         = {2024},
   OPTADDRESS   = {},
   OPTCROSSREF  = {},
   EDITOR       = {Romina Spalazzese and Heiko Koziolek},
   MONTH        = {June},
   NOTE         = {11 pages. ORO and ROR Functional Badges.},
   OPTNUMBER    = {},
   OPTORGANIZATION = {},
   PAGES        = {1--11},
   PUBLISHER    = {IEEE CS Press},
   OPTSERIES    = {},
   OPTVOLUME    = {},
   KEYWORDS     = {Topic: <b>Evolution patterns</b>, Venue: <c>ICSA</c>},
   URL          = {http://www.ptidej.net/publications/documents/ICSA24.doc.pdf},
   PDF          = {http://www.ptidej.net/publications/documents/ICSA24.ppt.pdf},
   ABSTRACT     = {Monolithic software systems face significant challenges 
      in terms of maintenance, scalability, and portability. To address 
      these challenges, many companies are embracing the microservices 
      architectural style as a more flexible alternative to their 
      monoliths. Microservices structure systems into modular, independent 
      components, enabling easier development, deployment, and maintenance. 
      However, the migration from a monolith to microservices is 
      challenging due to the laborious task of manually identifying and 
      decomposing a system into microservices. Several earlier studies 
      focused on developing approaches to facilitate the migration process. 
      However, the reliance on domain experts to define various parameters 
      and thresholds restricted their use. In this paper, we introduce 
      Magnet, a fully automated microservice identification approach, based 
      on graph neural networks (GNNs). Magnet integrates a GNN model with a 
      fine-grained method-based graph enriched with semantic and static 
      features of the system. It enables accurate microservices 
      identification while simultaneously promoting microservice cohesion 
      and reducing microservice coupling. To validate the accuracy of 
      Magnet, we performed extensive experiments using a set of open-source 
      systems. Quantitatively, we use a set of quality metrics to assess 
      the resulting microservices quality. We also compare our results to 
      established ground truths. Empirical evidence suggests that our 
      fully-automated approach Magnet achieves precision and recall rates 
      of 56\% and 68\%. Qualitatively, we assess the modularity and 
      functional independence of the resulting microservices by examining 
      their relationships and semantic integrity. This evaluation 
      demonstrates that our fully automated approach yields promising 
      results, underlining its effectiveness in creating modular and 
      coherent microservices.}
}

{"_id":"eBRKbW6zyjvMA3kdR","bibbaseid":"trabelsi-moha-guhneuc-geffard-magnetmethodbasedapproachusinggraphneuralnetworkformicroservicesidentification-2024","author_short":["Trabelsi, I.","Moha, N.","Gu�h�neuc, Y.","Geffard, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Imen"],"propositions":[],"lastnames":["Trabelsi"],"suffixes":[]},{"firstnames":["Naouel"],"propositions":[],"lastnames":["Moha"],"suffixes":[]},{"firstnames":["Yann-Ga�l"],"propositions":[],"lastnames":["Gu�h�neuc"],"suffixes":[]},{"firstnames":["Lucas"],"propositions":[],"lastnames":["Geffard"],"suffixes":[]}],"booktitle":"Proceedings of the 21^st International Conference on Software Architecture (ICSA)","title":"MAGNET: Method-based Approach using Graph Neural Network for Microservices Identification","year":"2024","optaddress":"","optcrossref":"","editor":[{"firstnames":["Romina"],"propositions":[],"lastnames":["Spalazzese"],"suffixes":[]},{"firstnames":["Heiko"],"propositions":[],"lastnames":["Koziolek"],"suffixes":[]}],"month":"June","note":"11 pages. ORO and ROR Functional Badges.","optnumber":"","optorganization":"","pages":"1–11","publisher":"IEEE CS Press","optseries":"","optvolume":"","keywords":"Topic: <b>Evolution patterns</b>, Venue: <c>ICSA</c>","url":"http://www.ptidej.net/publications/documents/ICSA24.doc.pdf","pdf":"http://www.ptidej.net/publications/documents/ICSA24.ppt.pdf","abstract":"Monolithic software systems face significant challenges in terms of maintenance, scalability, and portability. To address these challenges, many companies are embracing the microservices architectural style as a more flexible alternative to their monoliths. Microservices structure systems into modular, independent components, enabling easier development, deployment, and maintenance. However, the migration from a monolith to microservices is challenging due to the laborious task of manually identifying and decomposing a system into microservices. Several earlier studies focused on developing approaches to facilitate the migration process. However, the reliance on domain experts to define various parameters and thresholds restricted their use. In this paper, we introduce Magnet, a fully automated microservice identification approach, based on graph neural networks (GNNs). Magnet integrates a GNN model with a fine-grained method-based graph enriched with semantic and static features of the system. It enables accurate microservices identification while simultaneously promoting microservice cohesion and reducing microservice coupling. To validate the accuracy of Magnet, we performed extensive experiments using a set of open-source systems. Quantitatively, we use a set of quality metrics to assess the resulting microservices quality. We also compare our results to established ground truths. Empirical evidence suggests that our fully-automated approach Magnet achieves precision and recall rates of 56% and 68%. Qualitatively, we assess the modularity and functional independence of the resulting microservices by examining their relationships and semantic integrity. This evaluation demonstrates that our fully automated approach yields promising results, underlining its effectiveness in creating modular and coherent microservices.","bibtex":"@INPROCEEDINGS{Trabelsi24-ICSA-MAGNET,\r\n AUTHOR = {Imen Trabelsi and Naouel Moha and Yann-Ga�l Gu�h�neuc and \r\n Lucas Geffard},\r\n BOOKTITLE = {Proceedings of the 21^st International Conference on Software Architecture (ICSA)},\r\n TITLE = {MAGNET: Method-based Approach using Graph Neural Network \r\n for Microservices Identification},\r\n YEAR = {2024},\r\n OPTADDRESS = {},\r\n OPTCROSSREF = {},\r\n EDITOR = {Romina Spalazzese and Heiko Koziolek},\r\n MONTH = {June},\r\n NOTE = {11 pages. ORO and ROR Functional Badges.},\r\n OPTNUMBER = {},\r\n OPTORGANIZATION = {},\r\n PAGES = {1--11},\r\n PUBLISHER = {IEEE CS Press},\r\n OPTSERIES = {},\r\n OPTVOLUME = {},\r\n KEYWORDS = {Topic: <b>Evolution patterns</b>, Venue: <c>ICSA</c>},\r\n URL = {http://www.ptidej.net/publications/documents/ICSA24.doc.pdf},\r\n PDF = {http://www.ptidej.net/publications/documents/ICSA24.ppt.pdf},\r\n ABSTRACT = {Monolithic software systems face significant challenges \r\n in terms of maintenance, scalability, and portability. To address \r\n these challenges, many companies are embracing the microservices \r\n architectural style as a more flexible alternative to their \r\n monoliths. Microservices structure systems into modular, independent \r\n components, enabling easier development, deployment, and maintenance. \r\n However, the migration from a monolith to microservices is \r\n challenging due to the laborious task of manually identifying and \r\n decomposing a system into microservices. Several earlier studies \r\n focused on developing approaches to facilitate the migration process. \r\n However, the reliance on domain experts to define various parameters \r\n and thresholds restricted their use. In this paper, we introduce \r\n Magnet, a fully automated microservice identification approach, based \r\n on graph neural networks (GNNs). Magnet integrates a GNN model with a \r\n fine-grained method-based graph enriched with semantic and static \r\n features of the system. It enables accurate microservices \r\n identification while simultaneously promoting microservice cohesion \r\n and reducing microservice coupling. To validate the accuracy of \r\n Magnet, we performed extensive experiments using a set of open-source \r\n systems. Quantitatively, we use a set of quality metrics to assess \r\n the resulting microservices quality. We also compare our results to \r\n established ground truths. Empirical evidence suggests that our \r\n fully-automated approach Magnet achieves precision and recall rates \r\n of 56\\% and 68\\%. Qualitatively, we assess the modularity and \r\n functional independence of the resulting microservices by examining \r\n their relationships and semantic integrity. This evaluation \r\n demonstrates that our fully automated approach yields promising \r\n results, underlining its effectiveness in creating modular and \r\n coherent microservices.}\r\n}\r\n\r\n","author_short":["Trabelsi, I.","Moha, N.","Gu�h�neuc, Y.","Geffard, L."],"editor_short":["Spalazzese, R.","Koziolek, H."],"key":"Trabelsi24-ICSA-MAGNET","id":"Trabelsi24-ICSA-MAGNET","bibbaseid":"trabelsi-moha-guhneuc-geffard-magnetmethodbasedapproachusinggraphneuralnetworkformicroservicesidentification-2024","role":"author","urls":{"Paper":"http://www.ptidej.net/publications/documents/ICSA24.doc.pdf"},"keyword":["Topic: <b>Evolution patterns</b>","Venue: <c>ICSA</c>"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"http://www.yann-gael.gueheneuc.net/Work/Publications/Biblio/complete-bibliography.bib","dataSources":["8vn5MSGYWB4fAx9Z4"],"keywords":["topic: <b>evolution patterns</b>","venue: <c>icsa</c>"],"search_terms":["magnet","method","based","approach","using","graph","neural","network","microservices","identification","trabelsi","moha","gu�h�neuc","geffard"],"title":"MAGNET: Method-based Approach using Graph Neural Network for Microservices Identification","year":2024}