arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.00488cs.LGcs.DC
收藏

联邦模型异构Matryoshka表示学习

Federated Model Heterogeneous Matryoshka Representation Learning

College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);The University of British Columbia(不列颠哥伦比亚大学)

Liping Yi, Han Yu, Chao Ren, Gang Wang, Xiaoguang Liu, Xiaoxiao Li

AI总结:

针对模型异构联邦学习中知识交换受限的问题,提出FedMRL方法,通过辅助同构模型与轻量级投影器融合表示,并构建多维多粒度的Matryoshka表示,显著提升了模型准确率并降低了通信与计算成本。

摘要:

模型异构联邦学习(MHeteroFL)使FL客户端能够以分布式方式协作训练具有异构结构的模型。然而,现有的MHeteroFL方法依赖训练损失在客户端模型和服务器模型之间传递知识,导致知识交换受限。为了解决这一局限性,我们提出了用于监督学习任务的联邦模型异构Matryoshka表示学习方法(FedMRL)。它增加了一个由具有异构本地模型的客户端共享的辅助小型同构模型。(1)两个模型的特征提取器提取的广义和个性化表示,通过个性化的轻量级表示投影器进行融合。此步骤使表示融合能够适应本地数据分布。(2)然后使用融合的表示来构建Matryoshka表示,该表示具有由全局同构模型头和本地异构模型头学习的多维和多粒度嵌入表示。此步骤促进了多视角表示学习并提高了模型学习能力。理论分析表明,FedMRL实现了$O(1/T)$的非凸收敛率。在基准数据集上的大量实验表明,与七个最先进的基线相比,它在低通信和计算成本下具有卓越的模型准确性。与最先进的基线和同类别最佳基线相比,它分别实现了高达8.48%和24.94%的准确率提升。

英文摘要:

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHeteroFL methods rely on training loss to transfer knowledge between the client model and the server model, resulting in limited knowledge exchange. To address this limitation, we propose the Federated model heterogeneous Matryoshka Representation Learning (FedMRL) approach for supervised learning tasks. It adds an auxiliary small homogeneous model shared by clients with heterogeneous local models. (1) The generalized and personalized representations extracted by the two models' feature extractors are fused by a personalized lightweight representation projector. This step enables representation fusion to adapt to local data distribution. (2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header. This step facilitates multi-perspective representation learning and improves model learning capability. Theoretical analysis shows that FedMRL achieves a $O(1/T)$ non-convex convergence rate. Extensive experiments on benchmark datasets demonstrate its superior model accuracy with low communication and computational costs compared to seven state-of-the-art baselines. It achieves up to 8.48% and 24.94% accuracy improvement compared with the state-of-the-art and the best same-category baseline, respectively.

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。

↑