MicroRec: Leveraging Large Language Models for Microservice Recommendation
The increasing adoption of microservices in software development requires effective recommendation systems that guide developers to relevant microservices. In this paper, we introduce MicroRec, a novel microservice recommender framework which leveraging insights from Stack Overflow posts and the power of Large Language Models (LLMs). MicroRec utilizes a dual-encoder architecture that combines contrastive learning and semantic similarity learning, allowing us to achieve robust and accurate retrieval and ranking of relevant posts based on user queries. Using LLMs, MicroRec builds up a deep understanding of both user queries and microservices through the information they provides (e.g., README files and Dockerfiles). Our empirical evaluations demonstrate significant improvements brought by MicroRec over the existing methods across a variety of performance metrics including MRR, MAP, and precision@k. In addition, the results returned by MicroRec were fourteen times more accurate than those provided by the existing recommendation tool on the widely-used Docker Hub platform.
Mon 15 AprDisplayed time zone: Lisbon change
16:00 - 17:30 | Machine learning for Software EngineeringTechnical Papers at Grande Auditório Chair(s): Diego Costa Concordia University, Canada | ||
16:00 12mTalk | Whodunit: Classifying Code as Human Authored or GPT-4 Generated - A case study on CodeChef problems Technical Papers Oseremen Joy Idialu University of Waterloo, Noble Saji Mathews University of Waterloo, Canada, Rungroj Maipradit University of Waterloo, Joanne M. Atlee University of Waterloo, Mei Nagappan University of Waterloo DOI Pre-print | ||
16:12 12mTalk | GIRT-Model: Automated Generation of Issue Report Templates Technical Papers Nafiseh Nikehgbal Sharif University of Technology, Amir Hossein Kargaran LMU Munich, Abbas Heydarnoori Bowling Green State University DOI Pre-print | ||
16:24 12mTalk | MicroRec: Leveraging Large Language Models for Microservice Recommendation Technical Papers Ahmed Saeed Alsayed University of Wollongong, Hoa Khanh Dam University of Wollongong, Chau Nguyen University of Wollongong | ||
16:36 12mTalk | PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Software Technical Papers Wenxin Jiang Purdue University, Jerin Yasmin Queen's University, Canada, Jason Jones Purdue University, Nicholas Synovic Loyola University Chicago, Jiashen Kuo Purdue University, Nathaniel Bielanski Purdue University, Yuan Tian Queen's University, Kingston, Ontario, George K. Thiruvathukal Loyola University Chicago and Argonne National Laboratory, James C. Davis Purdue University DOI Pre-print | ||
16:48 12mTalk | Data Augmentation for Supervised Code Translation Learning Technical Papers Binger Chen Technische Universität Berlin, Jacek golebiowski Amazon AWS, Ziawasch Abedjan Leibniz Universität Hannover | ||
17:00 12mTalk | On the Effectiveness of Machine Learning-based Call-Graph Pruning: An Empirical Study Technical Papers Amir Mir Delft University of Technology, Mehdi Keshani Delft University of Technology, Sebastian Proksch Delft University of Technology Pre-print | ||
17:12 12mTalk | Leveraging GPT-like LLMs to Automate Issue Labeling Technical Papers Giuseppe Colavito University of Bari, Italy, Filippo Lanubile University of Bari, Nicole Novielli University of Bari, Luigi Quaranta University of Bari, Italy Pre-print | ||