发表机构
University of Glasgow（格拉斯哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对去中心化联邦学习中对等节点选择的不确定性，提出基于最优停止的SAGE选择器，通过锚定证据认证优势，在有限阶段做出决策，证明其性能不劣于随机闲聊，并显著降低探测与通信开销。
AI 中文摘要
去中心化联邦学习用对等节点间的模型交换取代了服务器聚合，使得协作者选择成为在不确定性下的局部决策。固定的探测预算在简单选择上浪费精力，而在对等节点难以区分时又力不从心。我们提出了SAGE（序贯锚定门控交换），一种在单模型承载交换预算下的最优停止对等节点选择器。接收方基于接收方持有的锚定证据对候选邻居进行评分，并在优势得到认证后做出选择。它仅在进一步证据能补偿其成本时继续探测，否则回退到随机闲聊。我们证明了该停止问题在有限阶段存在最优规则，且锚定调度在同伴风险差距和置信水平上达到阶最优。我们进一步证明，该选择器以高概率返回的同伴不会比随机闲聊更差，并证明对于未经认证就承诺的选择器，不存在此类保证。由此得出一个可分离性阈值，低于该阈值时任何探测预算都无法优于闲聊。实验涵盖两个图像基准、两个图族和三个异质性水平。在所有测试配置中，总是基于证据行动的选择器都输给了闲聊。SAGE-OS在比固定预算少75.5%的证据下匹配闲聊的性能，其通信开销仅为两个已发表选择器的一半。关键决策不在于哪个同伴应排第一，而在于证据是否足以支持排序。
英文摘要
Decentralised federated learning replaces server aggregation with peer-to-peer model exchange, making collaborator selection a local decision under uncertainty. Fixed probe budgets waste effort on easy choices yet fall short when peers are hard to distinguish. We propose SAGE (Sequential Anchor-Gated Exchange), an optimal-stopping peer selector under a one-model-bearing-exchange budget. A receiver scores candidate neighbours on receiver-owned anchor evidence and selects once an advantage is certified. It continues probing only while further evidence repays its cost, and otherwise falls back to random gossip. We show that the stopping problem admits an optimal rule attained at a finite stage, and that the anchor schedule is order-optimal in the peer-risk gap and the confidence level. We further show that the selector never returns a peer worse than random gossip with high probability, and prove that no such guarantee holds for selectors that commit without a certificate. A separability threshold follows, below which no probing budget improves on gossip. Experiments span two image benchmarks, two graph families and three heterogeneity levels. Selectors that always act on their evidence lose to gossip in every configuration tested. SAGE-OS matches gossip on 75.5% less evidence than a fixed budget, at half the communication overhead of two published selectors. The operative decision is not which peer to rank first, but whether the evidence justifies ranking at all.
Comments12 pages, 3 figures, 3 tables
