发表机构
School of Artificial Intelligence, Xidian University; School of Automation, Northwestern Polytechnical University; Faculty of Infor-X, Xidian University; College of Artificial Intelligence, Inner Mongolia Normal University（西安电子科技大学人工智能学院; 西北工业大学自动化学院; 西安电子科技大学Infor-X学院; 内蒙古师范大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有1比特联邦学习压缩方法忽略分层差异、无法捕捉细粒度参数变化的问题，提出分层多阈值随机Sketching方法，提升通信效率与通信-精度权衡性能。
AI 中文摘要
个性化联邦学习（PFL）是分布式设备上协同学习的有前景范式，边缘节点可在不共享原始数据的情况下协同训练个性化模型。尽管PFL通过学习客户端特定模型解决了数据异质性问题，但在带宽受限系统中交换高维参数时，仍存在巨大的上行和下行通信成本。近期的1比特方法实现了极致压缩，但通常依赖应用于整个模型的单一阈值规则，该设计存在两个局限：一是忽略了参数分布和量化敏感性的分层差异；二是单一阈值仅提供粗略的二元信息，无法捕捉参数分布的细粒度变化。为解决这些问题，我们提出一种基于分层多阈值随机Sketching的通信高效PFL框架。该方法为每一层分配专属的量化阈值集，使压缩表示可适配分层统计特性，同时利用多个区间为Sketching参数提供更精细的低比特描述；该方法支持使用紧凑低比特Sketching的双向通信，相比现有1比特压缩方法，提升了通信-精度权衡性能。
英文摘要
Personalized federated learning (PFL) is a promising paradigm for collaborative learning over distributed devices, where edge nodes collaboratively train personalized models without sharing raw data. Although PFL addresses data heterogeneity by learning client-specific models, it still suffers from substantial uplink and downlink communication costs when exchanging high-dimensional parameters in bandwidth-constrained systems. Recent one-bit methods achieve extreme compression, but they usually rely on a single thresholding rule applied to the whole model. This design has two limitations. First, it overlooks layer-wise differences in parameter distributions and quantization sensitivities. Second, a single threshold provides only coarse binary information and cannot capture fine-grained variations in parameter distributions. To address these issues, we propose a communication-efficient PFL framework via layer-wise multi-threshold random sketching. In the proposed method, each layer is assigned its own set of quantization thresholds, so that the compressed representation can adapt to layer-specific statistics while using multiple intervals to provide a finer low-bit description of sketched parameters. The proposed method supports bidirectional communication using compact low-bit sketches and improves the communication-accuracy tradeoff compared with existing one-bit compression approaches.
