Resource-Efficient Federated Hyperdimensional Computing
This addresses resource constraints in federated learning systems for edge computing applications, though it appears incremental as it builds on existing federated HDC methods.
The paper tackles the resource-performance tradeoff in federated hyperdimensional computing by proposing a framework that trains multiple smaller sub-models and refines them with a dropout-inspired procedure, achieving comparable or higher predictive performance while consuming less computational and wireless resources than baseline methods.
In conventional federated hyperdimensional computing (HDC), training larger models usually results in higher predictive performance but also requires more computational, communication, and energy resources. If the system resources are limited, one may have to sacrifice the predictive performance by reducing the size of the HDC model. The proposed resource-efficient federated hyperdimensional computing (RE-FHDC) framework alleviates such constraints by training multiple smaller independent HDC sub-models and refining the concatenated HDC model using the proposed dropout-inspired procedure. Our numerical comparison demonstrates that the proposed framework achieves a comparable or higher predictive performance while consuming less computational and wireless resources than the baseline federated HDC implementation.