2026-04-17T07:38:32Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4600612026-04-08T08:26:24Zcom_2072_1033col_2072_452950

Aggregating empirical evidence from data strategies studies: a case on model quantization Rey Juárez, Santiago del Medeiros dos Santos, Paulo Sérgio Travassos, Guilherme Horta 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 Software engineering Research synthesis Structured synthesis method Green AI Model quantization Background: As empirical software engineering evolves, more studies adopt data strategies—approaches that investigate digital artifacts such as models, source code, or system logs rather than relying on human subjects. Synthesizing results from such studies introduces new methodological challenges. Aims: This study assesses the effects of model quantization on correctness and resource efficiency in deep learning (DL) systems. Additionally, it explores the methodological implications of aggregating evidence from empirical studies that adopt data strategies. Method: We conducted a research synthesis of six primary studies that empirically evaluate model quantization. We applied the Structured Synthesis Method (SSM) to aggregate the findings, which combines qualitative and quantitative evidence through diagrammatic modeling. A total of 19 evidence models were extracted and aggregated. Results: The aggregated evidence indicates that model quantization weakly negatively affects correctness metrics while consistently improving resource efficiency metrics, including storage size, inference latency, and GPU energy consumption—a manageable trade-off for many DL deployment contexts. Evidence across quantization techniques remains fragmented, underscoring the need for more focused empirical studies per technique. Conclusions: Model quantization offers substantial efficiency benefits with minor trade-offs in correctness, making it a suitable optimization strategy for resource-constrained environments. This study also demonstrates the feasibility of using SSM to synthesize findings from data strategy-based research. 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. Prof. Travassos is a Brazilian CNPq researcher and CNE Faperj. Peer Reviewed Postprint (author's final draft) 2026 Conference report Del Rey, S. [et al.]. Aggregating empirical evidence from data strategies studies: a case on model quantization. A: International Symposium on Empirical Software Engineering and Measurement. «2025 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, ESEM 2025: 2-3 October 2025, Honolulu, United States: proceedings». Institute of Electrical and Electronics Engineers (IEEE), 2026, p. 12-22. ISBN 979-8-3315-9147-2. DOI 10.1109/ESEM64174.2025.00049 . 979-8-3315-9147-2 https://hdl.handle.net/2117/460061 10.1109/ESEM64174.2025.00049 eng https://ieeexplore.ieee.org/document/11323501 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 11 p. application/pdf Institute of Electrical and Electronics Engineers (IEEE)