A deep cut into Split Federated Self-supervised Learning
This work addresses privacy and efficiency issues in distributed machine learning for real-world collaborative scenarios, representing an incremental improvement over prior methods.
The paper tackled the problem of privacy and communication inefficiency in split federated self-supervised learning by showing that splitting depth is crucial and that existing methods like MocoSFL suffer from quality deterioration. They introduced MonAcoSFL, which achieved state-of-the-art accuracy while significantly reducing communication overhead.
Collaborative self-supervised learning has recently become feasible in highly distributed environments by dividing the network layers between client devices and a central server. However, state-of-the-art methods, such as MocoSFL, are optimized for network division at the initial layers, which decreases the protection of the client data and increases communication overhead. In this paper, we demonstrate that splitting depth is crucial for maintaining privacy and communication efficiency in distributed training. We also show that MocoSFL suffers from a catastrophic quality deterioration for the minimal communication overhead. As a remedy, we introduce Momentum-Aligned contrastive Split Federated Learning (MonAcoSFL), which aligns online and momentum client models during training procedure. Consequently, we achieve state-of-the-art accuracy while significantly reducing the communication overhead, making MonAcoSFL more practical in real-world scenarios.