ONNXPruner: ONNX-Based General Model Pruning Adapter
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5806-5817
DOI: 10.1109/tpami.2025.3554560 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Dongdong Ren und 7 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Young Elite Scientists Sponsorship Program by China Association for Science and Technology, Key Research and Development Program of Jiangsu Province.
Abstract (Originalsprache)
Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning.
Förderung
- National Natural Science Foundation of China
- Young Elite Scientists Sponsorship Program by China Association for Science and Technology
- Key Research and Development Program of Jiangsu Province
- Natural Science Foundation of Jiangsu Province
Zitieren
APA
Ren, D., Li, W., Ding, T., Wang, L., Fan, Q., Huo, J., Pan, H., & Gao, Y. (2025). ONNXPruner: ONNX-Based General Model Pruning Adapter. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5806-5817. https://doi.org/10.1109/tpami.2025.3554560
Vancouver
Ren D, Li W, Ding T, Wang L, Fan Q, Huo J, et al. ONNXPruner: ONNX-Based General Model Pruning Adapter. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5806-5817. doi:10.1109/tpami.2025.3554560
BibTeX
@article{Ren2025,
author = {Ren, Dongdong and Li, Wenbin and Ding, Tianyu and Wang, Lei and Fan, Qi and Huo, Jing and Pan, Hongbing and Gao, Yang},
title = {ONNXPruner: ONNX-Based General Model Pruning Adapter},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {7},
pages = {5806--5817},
doi = {10.1109/tpami.2025.3554560}
}
EUVIMED