为不同算力的客户端定制模型，提升联邦学习的适应性与性能
Representation-Aligned Multi-Scale Personalization for Federated Learning
- 用客户端描述生成专属轻量模型，避免固定全局主干
- 在视觉与图数据集上显著提升泛化能力与资源适配性
- 适合算力差异大的真实场景，尤其对边缘设备友好
在联邦学习中，如何应对资源各异的客户端仍是重大挑战。现有方法通常采用共享的全尺寸模型，由各客户端提取符合其算力预算的子模型，但此类方法依赖同一全局主干，限制了结构多样性与表征适应性。本文提出FRAMP框架，实现个性化且资源自适应的联邦学习：不再依赖固定全局模型，而是基于紧凑的客户端描述生成专属模型，实现对数据特征与计算预算的细粒度适配。每个客户端训练定制的轻量子模型，并对其学习到的表示进行对齐，以维持全局语义一致性。在视觉与图基准上的大量实验表明，FRAMP在多种客户端设置下均显著提升了泛化能力与适应性。
原文摘要 · Abstract (English)
In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use a shared full-size model, from which each client extracts a submodel aligned with its computational budget. However, regardless of the specific scoring strategy, these methods rely on the same global backbone, limiting both structural diversity and representational adaptation across clients. This paper presents FRAMP, a unified framework for personalized and resource-adaptive federated learning. Instead of relying on a fixed global model, FRAMP generates client-specific models from compact client descriptors, enabling fine-grained adaptation to both data characteristics and computational budgets. Each client trains a tailored lightweight submodel and aligns its learned representation with others to maintain global semantic consistency. Extensive experiments on vision and graph benchmarks demonstrate that FRAMP enhances generalization and adaptivity across a wide range of client settings.
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。