EdgeDRMM：去中心化联邦学习中的推理时专家转介协作
Learning to Refer: Inference-Time Collaboration in Decentralized Federated Learning
去中心化联邦学习里各客户端互相转介查询，不用中央调度也能汇总分布式专长，医疗数据实验结果不错，做分布式训练的可以看看。
一篇 arXiv 论文提出把去中心化联邦学习的推理时协作建模为带预算约束的本地专家转介问题：查询只能在相邻客户端之间流转，只有被访问过的客户端参与最终预测。EdgeDRMM 为每个客户端学习基于密度的路由势函数，利用相邻势能的差值选择转介路径，沿途聚合各本地模型的预测。训练与推理全程去中心化，仅依赖邻居本地信息，无需中央路由器或全局客户端打分。论文给出了所学比较的估计保证，并在基准数据与真实医疗数据上实验，结果显示 EdgeDRMM 在多数设置下优于图结构匹配的去中心化基线，稀疏连接场景下优势最明显。
Learning to Refer: Inference-Time Collaboration in Decentralized Federated Learning
In decentralized federated learning, heterogeneous clients may develop complementary expertise, yet each query is typically evaluated only by the client where it arrives. To exploit this distributed expertise without global coordination, we formulate inference-time collaboration as budgeted local expert referral, a graph-constrained routing process in which a query can move only between neighboring clients and only visited clients contribute to its final prediction. EdgeDRM implements this framework by learning a density-based routing potential for each client: differences between neighboring potentials provide the comparisons used to select successive referrals, while local task models generate predictions that are aggregated along the resulting route. Both training and inference are decentralized, using only neighbor-local information without a central router or graph-wide client scoring. We establish estimation guarantees for the learned comparisons and characterize how local improvement and graph structure govern prior-weighted density gains from referral. Experiments on benchmark and real-world medical data show that EdgeDRM outperforms graph-matched decentralized baselines in most settings, with the clearest benefits under sparse connectivity.
