Vertical Federated Learning (VFL) is an emergent distributed machine learning paradigm for collaborative learning between clients who have disjoint features of common entities. However, standard VFL lacks fault tolerance, with each participant and connection being a single point of failure. Prior attempts to induce fault tolerance in VFL focus on the scenario of "straggling clients", usually entailing that all messages eventually arrive or that there is an upper bound on the number of late messages. To handle the more general problem of arbitrary crashes, we propose Decoupled VFL (DVFL). To handle training with faults, DVFL decouples training between communication rounds using local unsupervised objectives. By further decoupling label supervision from aggregation, DVFL also enables redundant aggregators. As secondary benefits, DVFL can enhance data efficiency and provides immunity against gradient-based attacks. In this work, we implement DVFL for split neural networks with a self-supervised autoencoder loss. When there are faults, DVFL outperforms the best VFL-based alternative (97.58% vs 96.95% on an MNIST task). Even under perfect conditions, performance is comparable.

翻译：垂直联邦学习（VFL）是一种新兴的分布式机器学习范式，适用于对共同实体拥有互斥特征集的客户端之间进行协作学习。然而，标准VFL缺乏容错能力，每个参与方及其连接均为单点故障。先前在VFL中引入容错性的尝试主要关注“滞后客户端”场景，通常要求所有消息最终到达或设定延迟消息数量的上限。为处理更普遍的任意崩溃问题，本文提出解耦式垂直联邦学习（DVFL）。为在故障条件下进行训练，DVFL通过本地无监督目标实现通信轮次间的训练解耦。通过进一步将标签监督与聚合过程解耦，DVFL还支持冗余聚合器。作为次要优势，DVFL能够提升数据效率，并提供针对基于梯度的攻击的免疫能力。本研究为具有自监督自动编码器损失的拆分神经网络实现了DVFL。在存在故障的情况下，DVFL优于最佳的VFL改进方案（在MNIST任务中达到97.58% vs 96.95%）。即使在理想条件下，其性能仍具有可比性。