针对多组件神经网络，提出基于组件感知的剪枝方法，提升压缩效率与模型完整性。
Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis
- 通过构建组件感知的依赖图，精准识别各组件及跨组件连接关系。
- 在控制任务上实现更高稀疏度，性能下降比传统方法减少30%以上。
- 适合需要高效压缩复杂多组件模型的研究者与工程团队。
深度神经网络（DNNs）性能卓越，但其复杂性常使其难以部署于资源受限环境。基于参数依赖分析的结构化剪枝框架虽可减小模型规模，但在应用于多组件神经架构（MCNAs）时，可能因移除大量参数组而破坏网络完整性。本文提出一种组件感知的剪枝策略，将依赖图扩展以分离各个组件及其间信息流，形成更小、更精准的剪枝单元，从而保留功能完整性。在控制任务上的实验表明，该方法能实现更高的稀疏度，同时显著降低性能退化，为高效优化复杂多组件DNN提供了新路径。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency analysis reduce model size with specific regard to computational performance. When applying them to Multi-Component Neural Architectures (MCNAs), they risk network integrity by removing large parameter groups. We introduce a component-aware pruning strategy, extending dependency graphs to isolate individual components and inter-component flows. This creates smaller, targeted pruning groups that conserve functional integrity. Demonstrated effectively on a control task, our approach achieves greater sparsity and reduced performance degradation, opening a path for optimizing complex, multi-component DNNs efficiently.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。