利用卷积核对称性，仅传输关键参数，实现高效低损模型传输。
Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer
- 基于对称性约束的自由度编码，只传唯一系数，接收端可完全重建权重。
- 在量化与噪声信道下，压缩率更高且精度显著优于剪枝方法。
- 中心-反对称性表现最优，适合边缘设备间可靠模型传输。
本文研究通过利用卷积核中的结构化对称性来实现高效的神经网络通信传输。不传输所有模型参数，而是提出一种基于自由度（DoF）的编解码器，仅发送由选定对称群决定的唯一系数，可在接收端确定性地重构完整权重张量。该框架在多种对称模式、信噪比及位宽条件下，于量化和噪声信道中进行评估。为提升对传输损伤的鲁棒性，接收端进一步应用投影步骤，强制参数保持在对称不变子空间内，有效实现去噪。在MNIST和CIFAR-10数据集上使用DeepCNN架构的实验表明，基于DoF的传输方式在大幅降低带宽的同时，仍保持远高于剪枝基线的精度，后者常出现灾难性下降。在测试的对称性中， extit{central-skew symmetry}始终提供最佳的精度-压缩权衡，证实了结构冗余可用于在受限链路上实现可靠高效的模型交付。
原文摘要 · Abstract (English)
This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. Instead of transmitting all model parameters, we propose a degrees-of-freedom (DoF) based codec that sends only the unique coefficients implied by a chosen symmetry group, enabling deterministic reconstruction of the full weight tensor at the receiver. The proposed framework is evaluated under quantization and noisy channel conditions across multiple symmetry patterns, signal-to-noise ratios, and bit-widths. To improve robustness against transmission impairments, a projection step is further applied at the receiver to enforce consistency with the symmetry-invariant subspace, effectively denoising corrupted parameters. Experimental results on MNIST and CIFAR-10 using a DeepCNN architecture demonstrate that DoF-based transmission achieves substantial bandwidth reduction while preserving significantly higher accuracy than pruning-based baselines, which often suffer catastrophic degradation. Among the tested symmetries, \textit{central-skew symmetry} consistently provides the best accuracy-compression tradeoff, confirming that structured redundancy can be leveraged for reliable and efficient neural model delivery over constrained links.
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。