Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must handle heterogeneity in both client resources and local data distributions. Model-heterogeneous federated learning lowers client cost by allowing each client to train a subnet of a shared supernet, but most subnet-allocation policies are driven by device constraints and do not explicitly account for statistical heterogeneity. This paper proposes Heterogeneity-Aware Subnet Allocation (HASA), a train-only rule that assigns subnet widths based on client heterogeneity scores computed from local training data while enforcing a fixed size-weighted compute budget. This design enables budget-matched comparisons with alternative allocation policies. On an article-title next-word prediction benchmark with seven clients, HASA improves unweighted mean client test accuracy over uniform allocation across 10 matched seeds, increasing mean client test accuracy from 13.82 percent to 14.32 percent, and improves worst-client accuracy on average. In a matched-budget comparison with representative partial-training baselines, HASA achieves the strongest worst-client and tail-client accuracy on this benchmark. A directionality ablation shows that assigning smaller subnets to more heterogeneous clients degrades both mean and tail performance. A cross-domain image-classification study further shows that the effectiveness of heterogeneity-aware allocation depends on how well the heterogeneity score reflects clients' need for additional model width.

翻译：边缘服务日益采用联邦学习来在保护敏感数据本地化的同时，个性化设备端模型。实际部署中必须同时处理客户端资源与本地数据分布的异构性。模型异构联邦学习通过允许每个客户端训练共享超网的子网来降低客户端开销，但现有子网分配策略主要受设备约束驱动，未显式考虑统计异构性。本文提出异构感知子网分配策略（HASA），这是一种仅训练时生效的规则，基于从本地训练数据计算的客户端异构性得分分配子网宽度，同时强制执行固定的大小加权计算预算。该设计使得与替代分配策略的预算匹配比较成为可能。在包含七个客户端的文章标题下一词预测基准测试中，HASA在10个匹配随机种子上的未加权平均客户端测试准确率较均匀分配提升0.5个百分点（从13.82%提升至14.32%），且平均改善了最差客户端准确率。在与代表性部分训练基线方法的匹配预算比较中，HASA在该基准测试中实现了最强的最差客户端与尾端客户端准确率。方向性消融实验表明，将更小子网分配给异构性更强的客户端会降低平均与尾端性能。跨领域图像分类研究进一步表明，异构感知分配的有效性取决于异构性得分是否能准确反映客户端对额外模型宽度的需求。