Does Combining Parameter‐Efficient Modules Improve Few‐Shot Transfer Accuracy?
Artificial Intelligence for Engineering · 2025
DOI: 10.1049/aie2.12002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence for Engineering, 2025. Verfasst von Nader Asadi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Parameter‐efficient fine‐tuning has become a key technique for adapting large language and vision models to diverse downstream tasks, including emerging applications in engineering, such as design optimisation, fault detection in complex systems, material property prediction and autonomous robotics control. Specifically, the efficiency of low‐rank adaptation has facilitated the creation and sharing of hundreds of custom low‐rank adaptation (LoRA) modules, each trained on distinct data from various downstream tasks. In this paper, we explore the composability of LoRA modules, examining if combining these pre‐trained modules enhances generalisation to unseen downstream tasks. Our investigation involves evaluating two approaches: (a) uniform composition , involving averaging upstream LoRA modules with equal weights and (b) learned composition , where we learn the weights for each upstream module and perform weighted averaging. Through experiments on both vision and language models, we demonstrate that in few‐shot settings—common in many engineering workflows such as structural design, material discovery and system diagnostics—both composition methods consistently outperform full fine‐tuning and training LoRA from scratch. Moreover, in full‐shot settings, learned composition matches the performance of standard LoRA training while requiring significantly fewer trainable parameters. These results highlight the potential of compositional parameter‐efficient adaptation as a scalable and flexible approach for AI‐driven engineering tasks, enabling faster deployment, reduced data requirements and improved model reusability across diverse domains.
Zitieren
APA
Asadi, N., Beitollahi, M., Khalil, Y., Li, Y., Zhang, G., & Chen, X. (2025). Does Combining Parameter‐Efficient Modules Improve Few‐Shot Transfer Accuracy?. Artificial Intelligence for Engineering. https://doi.org/10.1049/aie2.12002
Vancouver
Asadi N, Beitollahi M, Khalil Y, Li Y, Zhang G, Chen X. Does Combining Parameter‐Efficient Modules Improve Few‐Shot Transfer Accuracy?. Artificial Intelligence for Engineering. 2025. doi:10.1049/aie2.12002
BibTeX
@article{Asadi2025,
author = {Asadi, Nader and Beitollahi, Mahdi and Khalil, Yasser and Li, Yinchuan and Zhang, Guojun and Chen, Xi},
title = {Does Combining Parameter‐Efficient Modules Improve Few‐Shot Transfer Accuracy?},
journal = {Artificial Intelligence for Engineering},
year = {2025},
doi = {10.1049/aie2.12002}
}
EUVIMED