arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.07078cs.LGmath.OC
收藏

个性化联邦学习中的共享表示

Exploiting Shared Representations for Personalized Federated Learning

The University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Pennsylvania(宾夕法尼亚大学)

Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai

摘要:

深度神经网络已经显示出从图像和文本等数据中提取通用特征表示的能力,这些特征表示对各种学习任务都很有用。然而,表示学习的成果还没有在联邦环境中完全实现。尽管联邦设置中的数据通常是非i.i.d.的。集中式深度学习在客户端上的成功表明,数据通常共享全局特征表示,而客户端或任务之间的统计异质性集中在标签中。基于这种直觉,我们提出了一种新的联邦学习框架和算法,用于学习跨客户端的共享数据表示和每个客户端的唯一本地头。我们的算法利用客户端的分布式计算能力来执行许多本地更新的表示的每一个更新的低维局部参数。我们证明了该方法在线性设置中以接近最优的样本复杂度线性收敛到地面真实表示,表明它可以有效地降低每个客户端的问题维度。这一结果的意义超出了联邦学习的范围,涉及到广泛的一类问题,我们的目标是在数据分布中学习共享的低维表示,例如在元学习和多任务学习中。此外,大量的实验结果表明,我们的方法在联邦环境中异构数据的替代个性化联邦学习方法的经验改进。

英文摘要:

Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be fully-realized in federated settings. Although data in federated settings is often non-i.i.d. across clients, the success of centralized deep learning suggests that data often shares a global feature representation, while the statistical heterogeneity across clients or tasks is concentrated in the labels. Based on this intuition, we propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client. Our algorithm harnesses the distributed computational power across clients to perform many local-updates with respect to the low-dimensional local parameters for every update of the representation. We prove that this method obtains linear convergence to the ground-truth representation with near-optimal sample complexity in a linear setting, demonstrating that it can efficiently reduce the problem dimension for each client. This result is of interest beyond federated learning to a broad class of problems in which we aim to learn a shared low-dimensional representation among data distributions, for example in meta-learning and multi-task learning. Further, extensive experimental results show the empirical improvement of our method over alternative personalized federated learning approaches in federated environments with heterogeneous data.

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。

↑