为异构物联网联邦学习设计高效模型适配方法，训练快、通信少、性能强。
DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training
- 用多目标优化引导超网络训练，提前存优架构提升效率
- 搜索仅需20秒，比基线快61倍，准确率最高提升1.21%
- 适合资源受限的物联网场景，抗数据分布不均
在异构物联网设备群上部署联邦学习需为每类设备定制神经网络架构，但现有联邦神经架构搜索（FedNAS）方法存在超网络训练无指引、搜索流程成本高（单次部署需超20 GPU小时）的问题。本文提出DeepFedNAS，两阶段框架基于多目标适应度函数，融合信息论指标与架构启发式。第一阶段，联邦帕累托最优超网络训练以预计算的优质架构缓存替代随机子网采样，获得更优超网络；第二阶段，预测器无搜索利用该适应度函数作为零成本精度代理，可在约20秒内发现硬件优化子网，较基线提速约61倍。在CIFAR-10、CIFAR-100和CINIC-10上的实验表明，该方法实现最先进的准确率（CIFAR-100最高提升1.21%），每轮传输量减少2.8倍，并在极端非独立同分布条件（α = 0.1）下保持鲁棒性，适用于可扩展、通信受限的物联网联邦系统。源代码：https://github.com/bostankhan6/DeepFedNAS
原文摘要 · Abstract (English)
Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet training and prohibitively costly post-training search pipelines that demand over 20 GPU-hours per deployment target. We introduce DeepFedNAS, a two-phase framework built on a multi-objective fitness function that synthesizes information-theoretic network metrics with architectural heuristics. In the first phase, Federated Pareto Optimal Supernet Training replaces random subnet sampling with a pre-computed cache of elite, high-fitness architectures, yielding a superior supernet. In the second phase, a Predictor-Free Search uses this fitness function as a zero-cost accuracy proxy, discovering hardware-optimized subnets in ~20 seconds, a ~61x speedup over the baseline pipeline. Experiments on CIFAR-10, CIFAR-100, and CINIC-10 demonstrate state-of-the-art accuracy (up to +1.21% on CIFAR-100), a 2.8x reduction in per-round transmission size, and robust performance under extreme non-IID conditions (α = 0.1), making DeepFedNAS practical for scalable, communication-constrained IoT federations. Source code: https://github.com/bostankhan6/DeepFedNAS
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。