Leveraging Kernel Symmetry for Joint Compression and Error Mitigation in Edge Model Transfer

2026-04-19

AI Summary

This work addresses the challenges of high bandwidth requirements and susceptibility to channel noise in neural network transmission across edge devices by introducing, for the first time, structured symmetry in convolutional kernels into a joint compression and noise-resilient transmission framework. By transmitting only the independent degrees of freedom dictated by symmetry groups and reconstructing weights deterministically at the receiver through projection onto symmetry-invariant subspaces, the method achieves simultaneous bandwidth efficiency and error suppression. Evaluated on MNIST and CIFAR-10, the approach significantly reduces bandwidth demands while substantially outperforming pruning-based baselines in accuracy. Notably, the centrally skew-symmetric design strikes an optimal trade-off between compression ratio and model fidelity.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Adversarial Attacks & Robustness
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

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.

Problem

• model compression
• error mitigation
• symmetry constraints
• edge model transfer
• communication efficiency

Innovation

• kernel symmetry
• degrees-of-freedom codec
• symmetry-invariant subspace
• edge model transfer
• error mitigation