Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples
- Resource Type
- Conference
- Authors
- Sun, Jingwei; Xu, Ziyue; Yang, Dong; Nath, Vishwesh; Li, Wenqi; Zhao, Can; Xu, Daguang; Chen, Yiran; Roth, Holger R.
- Source
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV) ICCV Computer Vision (ICCV), 2023 IEEE/CVF International Conference on. :5180-5189 Oct, 2023
- Subject
- Computing and Processing
Signal Processing and Analysis
Computer vision
Costs
Codes
Federated learning
Semisupervised learning
Data models
Servers
- Language
- ISSN
- 2380-7504
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 VFL framework called 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 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× compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code is available at https://nvidia.github.io/NVFlare/research/one-shot-vfl.