发表机构
University of British Columbia; University of South Florida（不列颠哥伦比亚大学; 南佛罗里达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对模型压缩中稀疏度过高时性能骤降的问题，提出跨架构的BRIDGE框架，通过反向再生策略拓展压缩极限，在两类架构上实现显著性能提升。
AI 中文摘要
模型压缩对于将网络部署在资源受限的边缘设备上至关重要。尽管基于剪枝的方法能大幅减小模型体积，但它们往往在稀疏度超过阈值时出现性能骤降，导致难以确定模型的可行压缩极限。为应对这一挑战，我们提出了边界学习反向再生框架BRIDGE，将压缩问题重新表述为建设性边界搜索问题。与正向剪枝不同，我们的方法先将模型驱动至极度稀疏状态以暴露性能崩溃区域，再选择性地再生关键结构以恢复性能。该框架采用分层再生策略，包括粗粒度层选择与细粒度再生参数选择，以精准识别需恢复的参数。实验表明，我们的方法可在CNN和Transformer架构上从崩溃边缘恢复模型，展现出架构独立性；BRIDGE在非结构化剪枝中实现了最高1.49%的性能提升，在结构化剪枝中实现了最高4.77%的性能提升。这些结果证明，反向再生可在保持性能稳定的同时有效拓展压缩极限，源代码可在此URL获取。
英文摘要
Model compression is critical for deploying networks on resource-constrained edge devices. While pruning-based methods can significantly reduce model size, they often suffer from abrupt performance collapse beyond a sparsity thresh-old, making it difficult to identify the feasible compression limit of the model. To address this challenge, we propose a boundary-Learning reverse regrowth framework, BRIDGE, that reformulates compression as a constructive boundary-search problem. Unlike forward pruning, our method first drives the model to an extremely sparse state to expose the collapse region, and then selectively regenerates the critical structure to restore performance. The proposed framework employs a hierarchical regeneration strategy, including coarse-grained layer selection and fine-grained regeneration parameter selection, to accurately identify which parameters require recovery. Experiments show that our method can recover models from the brink of collapse on both CNNs and Transformer architectures, demonstrating its architecture in-dependence. BRIDGE achieves a performance improvement of up to 1.49% in unstructured pruning and up to 4.77% in structured pruning. These results demonstrate that reverse regeneration can effectively extend the compression limit while maintaining stable performance. The source code is available at https://github.com/EnumaCaliber/BRIDGE.
CommentsWithdrawn by the authors following the identification of issues in the analysis and results that may materially affect the conclusions of the manuscript
