Communication and Storage Efficient Coded CNN Inference for Straggler-Resistant Over IoT Devices

This paper proposes the Low Upload and Storage Cost (LUSC) scheme, a coded distributed computing (CDC) approach that accelerates Convolutional Neural Network (CNN) inference on resource-constrained edge devices. LUSC introduces a new encoding and decoding mechanism that exploits the periodicity and evenness of cosine functions, reducing communication and storage overhead while ensuring numerical stability. Orthogonal decoding matrices derived from this cosine-based design guarantee stable inversion and preserve numerical precision. By leveraging the duality property of cosine functions, LUSC reduces the number of workers required for decoding, enabling finer-grained task decomposition and further lowering upload and storage costs. When combined with a spatial and channel grid partition (SCGP) strategy, LUSC (including other matrix-multiplication-based CDC schemes) can be applied to convolutions, accelerating CNN inference while maintaining resilience to stragglers. Experimental results demonstrate that LUSC consistently outperforms existing numerically stable CDC schemes, providing efficient inference with reduced communication and storage costs and maintaining robustness under straggler conditions.