让边缘设备学会信任邻居，提升推理时的协作效果。
Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning
- 每个设备自学习邻居可信度，动态决定是否协作。
- 在多个数据集和网络结构上，部署准确率显著优于基线。
- 通信量少，适合资源受限的物联网场景。
许多去中心化蒸馏方法依赖训练期协调，但在推理时却孤立部署，即使更强的邻居可用。在物联网等异构、数据稀疏且分布不均的场景中，节点的最优邻居可能远超其本地能力。本文研究如何训练节点以使其预测在部署时能良好组合，并学习信任谁。在无服务器、模型无关的协议下，节点仅交换查询和软预测，提出学习型邻居可信度（LNTrust）：每个节点基于本地验证证据，学习一个紧凑的邻居可信度函数。该函数在训练时控制辅助蒸馏，在推理时构建集成策略，使训练中习得的协作直接迁移至部署。在多种数据集与拓扑结构下，LNTrust相比最强输出基线显著提升部署准确率，同时通信开销远低于以往方法。
原文摘要 · Abstract (English)
Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at inference time. This is an incomplete objective for settings such as IoT, where devices are heterogeneous, data is scarce and skewed, and a node's strongest neighbors may far exceed its own local capacity. We study how nodes should train so that their predictions compose well at deployment, and how each node should learn whom to trust. Under a server-free, model-agnostic protocol where nodes exchange only queries and soft predictions, we propose Learned Neighbor Trust (LNTrust) wherein each node learns a compact trust function over its neighborhood from local validation evidence. This trust function gates auxiliary distillation during training and defines a deployment ensemble at inference, so that collaboration learned during training transfers directly to deployment. Across datasets and topologies, LNTrust improves deployed accuracy over the strongest output-only baseline by large margins while using significantly less communication than previous methods.
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。