2026-04-17T20:25:23Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4601472026-04-03T06:37:52Zcom_2072_1033col_2072_452950

Addressing quality challenges in deep learning: The role of MLOps and domain knowledge Rey Juárez, Santiago del Medina i Díez, Adrià Franch Gutiérrez, Javier Martínez Fernández, Silverio Juan Universitat Politècnica de Catalunya. Doctorat en Computació Universitat Politècnica de Catalunya. Departament d'Enginyeria de Serveis i Sistemes d'Informació Universitat Politècnica de Catalunya. inSSIDE - integrated Software, Services, Information and Data Engineering Àrees temàtiques de la UPC::Informàtica::Enginyeria del software Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic SE4AI MLOps Software engineering Artificial intelligence Quality attributes Deep learning (DL) systems present unique challenges in software engineering, especially concerning quality attributes like correctness and resource efficiency. While DL models excel in specific tasks, engineering DL systems is still essential. The effort, cost, and potential diminishing returns of continual improvements must be carefully evaluated, as software engineers often face the critical decision of when to stop refining a system relative to its quality attributes. This experience paper explores the role of MLOps practices¿such as monitoring and experiment tracking¿in creating transparent and reproducible experimentation environments that enable teams to assess and justify the impact of design decisions on quality attributes. Furthermore, we report on experiences addressing the quality challenges by embedding domain knowledge into the design of a DL model and its integration within a larger system. The findings offer actionable insights into the benefits of domain knowledge and MLOps and the strategic consideration of when to limit further optimizations in DL projects to maximize overall system quality and reliability. This work is partially supported by the GAISSA project TED2021-130923B-I00, funded by MCIN/AEI/10.13039/501100011033 and the European Union Next Generation EU/PRTR. It is also partially funded by the Joan Oró pre-doctoral support program (BDNS 657443), co-funded by the European Union. Peer Reviewed Postprint (author's final draft) 2025 Conference lecture Del Rey, S. [et al.]. Addressing quality challenges in deep learning: The role of MLOps and domain knowledge. A: International Conference on AI Engineering - Software Engineering for AI. «2025 IEEE/ACM 4th International Conference on AI Engineering – Software Engineering for AI, CAIN 2025: Ottawa, Ontario, Canada, 27-28 April 2025: proceedings». Institute of Electrical and Electronics Engineers (IEEE), 2025, p. 184-189. ISBN 979-8-3315-0219-5. DOI 10.1109/CAIN66642.2025.00029 . 979-8-3315-0219-5 https://hdl.handle.net/2117/460147 10.1109/CAIN66642.2025.00029 https://hdl.handle.net/2117/460147 eng https://ieeexplore.ieee.org/document/11030036 info:eu-repo/grantAgreement/AEI/PLAN ESTATAL DE INVESTIGACIÓN CIENTÍFICA Y TÉCNICA Y DE INNOVACIÓN 2021-2023/TED2021-130923B-I00/GAISSA. Transición hacia sistemas de software verdes basados en IA: un enfoque centrado en arquitectura Open Access 6 p. application/pdf Institute of Electrical and Electronics Engineers (IEEE)