From Legacy to Microservices: a Type-based Approach for Microservice Identification using ML and Semantic Analysis [2022]

This paper propose a framework, called MicroMiner, a microservices identification approach that is based on static-relationship analyses between code elements as well as semantic analyses of the source code. It is relies on machine learning (ML) techniques

Imen Trabelsi, Manel Abdellatif, Abdalgader Abubaker, Naouel Moha, Sébastien Mosser, Samira Ebrahimi‐Kahou, Yann‐Gaël Guéhéneuc

Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networks [2023]

This work present SPHH, a novel self-supervised pretraining framework for heterogeneous HyperGNNs. Our method is able to effectively capture higher-order relations among entities in the data in a self-supervised manner. SPHH is consist of two self-supervised pretraining tasks that aim to simultaneously learn both local and global representations of the entities in the hypergraph by using informative representations derived from the hypergraph structure.

Abdalgader Abubaker, Takanori Maehara, Madhav Nimishakavi, Vassilis Plachouras