多级联邦学习中的个性化加法建模
Personalized Additive Modeling for Multi-level Federated Learning
AI总结：
本文提出FeMAM，通过多级共享模型和加法组合构建个性化预测器，有效处理复杂非独立同分布数据，优于传统联邦学习基线。
摘要：
现代AI面临在通用性与用户特定个性化之间的平衡挑战。在联邦学习（FL）中，这一挑战因高度异质的客户端数据和复杂的非IID模式而加剧。现有FL方法受限于固定的异质性设置，难以应对复杂结构。本文从多级非IID视角出发，通过全局、子组和客户端特定组件捕捉客户端相似性，提出FeMAM，通过动态增长和剪枝模型，以低成本实现多级共享模型和个性化预测器，实验显示其在复杂非IID结构中表现优异。
英文摘要：
Contemporary AI faces the challenge of balancing generality with user-specific personalization. In federated learning (FL), this challenge is amplified by highly heterogeneous client data with complex non-IID patterns beyond standard IID assumptions. Many existing FL methods are designed for relatively restricted heterogeneity settings (e.g., a fixed number of clusters or a fixed form of personalization), limiting their robustness under complex structures. In this work, we study FL from a \emph{multi-level non-IID} perspective, where client similarity is captured by multiple granularities of shared knowledge: global, subgroup, and client-specific components. This view captures coarse-to-fine relationships while requiring less prior knowledge of task boundaries. Building on this insight, we propose \emph{Federated Multi-level Additive Modeling} (FeMAM), which learns multiple levels of shareable models and constructs personalized predictors via additive composition across levels. To move beyond a fixed structure, FeMAM allows models to grow and be pruned dynamically during training, adapting to diverse federated scenarios. Despite employing multiple models, FeMAM remains cost-friendly by unlocking only a small subset (one level) of models for training at a time. Extensive experiments show that FeMAM effectively approximates diverse complex non-IID structures and consistently outperforms representative clustered and personalized FL baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
