Fed-MIWAE：通过深度生成模型对不完整数据进行联邦插补
Fed-MIWAE: Federated Imputation of Incomplete Data via Deep Generative Models
AI总结：
本文提出 Fed-MIWAE，将深度生成模型 MIWAE 联邦化，用于在不交换原始数据的前提下对分布式不完整数据进行插补，并在 ADNI 多模态医学数据上验证其精度接近集中式最优方法且能量化插补不确定性。
摘要：
联邦学习允许在多个分散的本地数据集上训练机器学习模型，而无需显式交换数据。然而，数据预处理（包括处理缺失数据的策略）仍然是现实世界联邦学习部署中的主要瓶颈，并且通常在本地执行。这种方法可能存在偏差，因为每个中心本地观察到的子群体可能无法代表整体群体。为了解决这个问题，本文首先提出了一种通过联邦模型实现更一致的数据标准化方法。此外，我们提出了 Fed-MIWAE，这是最先进的插补方法 MIWAE 的联邦版本，MIWAE 是一种基于变分自编码器的深度潜变量模型，用于缺失数据插补。MIWAE 的一大优势是可以用经典的联邦聚合器轻松训练。此外，它能够处理 MAR（随机缺失）数据，这是一种比 MCAR（完全随机缺失）更具挑战性的缺失数据机制，在 MAR 中变量的缺失可能依赖于已观测到的变量。我们在模拟联邦场景下，使用 ADNI 数据集的多模态医学影像数据和临床评分来评估我们的方法。我们将 Fed-MIWAE 与在本地或以集中式方式执行的经典插补方法进行比较。即使本地数据分布高度异质，Fed-MIWAE 也能实现与最佳集中式方法相当的插补精度。此外，由于 Fed-MIWAE 的变分特性，我们的方法被设计用于执行多重插补，从而能够在联邦场景中量化插补不确定性。
英文摘要：
Federated learning allows for the training of machine learning models on multiple decentralized local datasets without requiring explicit data exchange. However, data pre-processing, including strategies for handling missing data, remains a major bottleneck in real-world federated learning deployment, and is typically performed locally. This approach may be biased, since the subpopulations locally observed at each center may not be representative of the overall one. To address this issue, this paper first proposes a more consistent approach to data standardization through a federated model. Additionally, we propose Fed-MIWAE, a federated version of the state-of-the-art imputation method MIWAE, a deep latent variable model for missing data imputation based on variational autoencoders. MIWAE has the great advantage of being easily trainable with classical federated aggregators. Furthermore, it is able to deal with MAR (Missing At Random) data, a more challenging missing-data mechanism than MCAR (Missing Completely At Random), where the missingness of a variable can depend on the observed ones. We evaluate our method on multi-modal medical imaging data and clinical scores from a simulated federated scenario with the ADNI dataset. We compare Fed-MIWAE with respect to classical imputation methods, either performed locally or in a centralized fashion. Fed-MIWAE allows to achieve imputation accuracy comparable with the best centralized method, even when local data distributions are highly heterogeneous. In addition, thanks to the variational nature of Fed-MIWAE, our method is designed to perform multiple imputation, allowing for the quantification of the imputation uncertainty in the federated scenario.
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。
