AI 中文总结
提出FedHV，用闭式逆松弛权重实现低通信开销的联邦多目标优化，在多个非IID视觉任务上优于现有方法。
AI 中文摘要
任务级联邦多目标优化（FedMOO）在异构数据、部分参与和通信约束下训练一个共享模型以应对相互竞争的预测目标。现有方法通常从梯度或更新几何中推导任务权重，这需要任务特定信息或迭代的服务器端优化。我们提出FedHV，将参考相对目标松弛映射为闭式逆松弛权重。每个客户端优化一个加权损失，并随模型更新返回目标估计。该协议为每个参与客户端恰好增加2m个辅助标量，使得每客户端总通信量为Theta(d + m)，而FSMGDA的任务特定通信量为Theta(md)，且无需额外的同步阶段。我们在客户端异构性、多步本地更新、部分参与和有限样本目标报告下分析了由此产生的单轮延迟权重。在固定时域正松弛参考条件下，配合规定的时域相关步长和趋于零的报告误差，FedHV对平均平方对数超体积梯度范数达到O(T^(-1/2))的收敛率；持续的报告误差决定了最终的平稳性邻域。相同的界也控制平方帕累托平稳性残差。在来自四个视觉基准族和三个训练种子的六个Dirichlet划分的非IID设置中，FedHV在五个设置中的平均准确率超过FSMGDA和FedCMOO。在这些方法和均匀标量化中，它在四个设置中实现了最高的最差任务准确率，并在两个CIFAR10-MNIST设置中改善了困难的CIFAR-10目标。
英文摘要
Task-wise federated multi-objective optimization (FedMOO) trains a shared model for competing prediction objectives under heterogeneous data, partial participation, and communication constraints. Existing methods commonly derive task weights from gradient or update geometry. This requires task-specific information or iterative server-side optimization. We introduce FedHV, which maps reference-relative objective slacks to closed-form inverse-slack weights. Each client optimizes one weighted loss and returns objective estimates with its model update. The protocol adds exactly 2m auxiliary scalars per participating client, yielding Theta(d + m) total per-client communication, compared with the Theta(md) task-specific communication of FSMGDA, and requires no additional synchronization stage. We analyze the resulting one-round-delayed weights under client heterogeneity, multi-step local updates, partial participation, and finite-sample objective reports. Under a fixed-horizon positive-slack reference condition, with the prescribed horizon-dependent step size and vanishing report error, FedHV achieves an O(T^(-1/2)) rate for the average squared log-hypervolume gradient norm; persistent report error determines the resulting stationarity neighborhood. The same bound controls the squared Pareto-stationarity residual. Across six Dirichlet-partitioned non-IID settings from four vision benchmark families and three training seeds, FedHV exceeds FSMGDA and FedCMOO in mean accuracy in five settings. Among these methods and uniform scalarization, it achieves the highest worst-task accuracy in four settings and improves the difficult CIFAR-10 objective in both CIFAR10-MNIST settings.
CommentsPreprint; submitted to ICLR 2027
