Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer
This work addresses the problem of efficient and reliable neural network transmission over constrained links for edge deployment, offering a novel compression method that exploits structured redundancy.
The paper proposes a degrees-of-freedom (DoF) based codec that leverages kernel symmetry to compress neural network models for edge transmission, achieving substantial bandwidth reduction while preserving higher accuracy than pruning-based baselines, with central-skew symmetry providing the best tradeoff.
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.