Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples
This addresses communication bottlenecks and data scarcity in vertical federated learning, which is crucial for privacy-preserving collaborative AI in domains like healthcare or finance, though it appears incremental as it builds on existing VFL and semi-supervised learning concepts.
The paper tackles the high communication costs and inefficiency with limited overlapping samples in vertical federated learning by proposing one-shot and few-shot VFL frameworks, achieving over 46.5% accuracy improvement and more than 330x reduction in communication cost on CIFAR-10 compared to state-of-the-art methods.
Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical vertical federated learning (VFL) framework called \textbf{one-shot VFL} that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose \textbf{few-shot VFL} to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5\% and reduce the communication cost by more than 330$\times$ compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code will be made publicly available at \url{https://nvidia.github.io/NVFlare/research/one-shot-vfl}.