量化让航天预测维护的联邦学习更省带宽，INT4几乎不损失精度。
Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenance
- 用不同位数量化梯度，测试精度与通信开销的平衡。
- INT4比32位精度几乎没下降，通信量减少8倍至4.73KiB/轮。
- 非独立同分布数据下才能真实评估量化稳定性，适合航天场景部署。
联邦学习（FL）可在分布式航空机队中实现隐私保护的预测性维护，但梯度通信开销限制了在带宽受限的物联网节点上的部署。本文研究对称均匀量化（$b \in \{32,8,4,2\}$位）对定制轻量级一维卷积模型（AeroConv1D，9697参数）在NASA C-MAPSS基准上基于真实非独立同分布（Non-IID）客户端划分的联邦学习精度-效率权衡的影响。通过严格的多种子评估（$N=10$），结果表明：INT4在FD001（$p=0.341$）和FD002（$p=0.264$ MAE，$p=0.534$ NASA评分）上与FP32统计无差异，同时实现8倍通信成本降低（从37.88 KiB降至4.73 KiB/轮）。关键发现是：朴素的IID划分会人为抑制方差；正确的Non-IID评估揭示了极端量化的真实操作不稳定性，通过直接的IID vs. Non-IID对比验证。INT2被实证证明不适用：虽在FD002上因极强正则化导致更低的MAE，但伴随灾难性NASA评分波动（变异系数45.8%对比FP32的22.3%），证实其在异构工况下不可复现。基于Xilinx ZCU102的FPGA资源分析显示，INT4可满足硬件约束（85.5% DSP利用率），有望实现单片SoC上的完整FL流水线。完整仿真代码与FPGA估算脚本已开源：https://github.com/therealdeadbeef/aerospace-fl-quantization。
原文摘要 · Abstract (English)
Federated learning (FL) enables privacy-preserving predictive maintenance across distributed aerospace fleets, but gradient communication overhead constrains deployment on bandwidth-limited IoT nodes. This paper investigates the impact of symmetric uniform quantization ($b \in \{32,8,4,2\}$ bits) on the accuracy--efficiency trade-off of a custom-designed lightweight 1-D convolutional model (AeroConv1D, 9\,697 parameters) trained via FL on the NASA C-MAPSS benchmark under a realistic Non-IID client partition. Using a rigorous multi-seed evaluation ($N=10$ seeds), we show that INT4 achieves accuracy \emph{statistically indistinguishable} from FP32 on both FD001 ($p=0.341$) and FD002 ($p=0.264$ MAE, $p=0.534$ NASA score) while delivering an $8\times$ reduction in gradient communication cost (37.88~KiB $\to$ 4.73~KiB per round). A key methodological finding is that naïve IID client partitioning artificially suppresses variance; correct Non-IID evaluation reveals the true operational instability of extreme quantization, demonstrated via a direct empirical IID vs.\ Non-IID comparison. INT2 is empirically characterized as unsuitable: while it achieves lower MAE on FD002 through extreme quantization-induced over-regularization, this apparent gain is accompanied by catastrophic NASA score instability (CV\,=\,45.8\% vs.\ 22.3\% for FP32), confirming non-reproducibility under heterogeneous operating conditions. Analytical FPGA resource projections on the Xilinx ZCU102 confirm that INT4 fits within hardware constraints (85.5\% DSP utilization), potentially enabling a complete FL pipeline on a single SoC. The full simulation codebase and FPGA estimation scripts are publicly available at https://github.com/therealdeadbeef/aerospace-fl-quantization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。