Loading
Life sciences · Preprint
arXiv · August 14, 2026
Posted before peer review. The findings may change or fail to hold.
This preprint proposes a polar code–based federated learning scheme that applies unequal error protection to quantization bits to improve robustness under channel noise, backed by convergence analysis and experimental comparison to uncoded and LDPC baselines. The work is theoretical and computational, not a clinical or human-subjects trial, and remains unrefereed.
Preprint. Intervention: Polar code–based federated learning scheme with unequal error protection applied to quantization bits; joint optimization of quantization bit depth and polar code block length across training iterations.. Compared with: Uncoded transmission and LDPC-based equal error protection (EEP) schemes..
Polar code scheme with unequal error protection (UEP) selectively protects more significant quantization bits to mitigate channel noise effects. Convergence analysis derives an upper bound on the convergence gap, jointly optimized over quantization bits and polar code block length. Experimental results show substantial performance gains over uncoded and LDPC-based equal error protection (EEP) benchmarks, with advantage increasing as channel quality deteriorates.
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is a preprint technical contribution on federated learning optimization under channel noise, with theoretical convergence analysis and computational experiments, but it has not undergone peer review.
As stated by the source record.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
What is missing. This record has no reported figures. That is a gap in the analysis, not a judgement about the study.
Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data; however, it faces significant communication bottlenecks and channel impairments in practice. Conventional network layer treatments either idealize the channel as error free or apply equal error protection (EEP) to transmitted model updates, failing to account for the inherently unequal importance of quantization bits within a single local model. To address this limitation, we propose a cross layer polar code based FL scheme that leverages the unequal error protection (UEP) property of polar codes under finite block lengths. Specifically, the proposed design selectively protects more significant quantization bits, thereby mitigating the detrimental effects of channel noise. We further provide a rigorous convergence analysis of the proposed scheme, deriving an upper bound on the convergence gap, which we then jointly optimize over the number of quantization bits and the polar code block length across all training iterations. Experimental results demonstrate that both constant and variable block length configurations of our polar code based scheme consistently achieve substantial performance gains over uncoded and LDPC-based EEP benchmarks, with the advantage becoming increasingly pronounced as the channel quality deteriorating. These findings confirm the efficacy of our cross-layer design in enhancing FL robustness and efficiency under realistic channel conditions.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.