VFL-RPS: Relevant Participant Selection in Vertical Federated Learning
This addresses the challenge of efficient collaboration in VFL for data owners with different features, though it is incremental by focusing on a gap in participant selection methods.
The paper tackles the problem of selecting helpful participants in Vertical Federated Learning (VFL) to improve model performance, proposing VFL-RPS as a pre-training method that achieves comparable results to using all data with only a few participants and outperforms existing VFL selection methods.
Federated Learning (FL) allows collaboration between different parties, while ensuring that the data across these parties is not shared. However, not every collaboration is helpful in terms of the resulting model performance. Therefore, it is an important challenge to select the correct participants in a collaboration. As it currently stands, most of the efforts in participant selection in the literature have focused on Horizontal Federated Learning (HFL), which assumes that all features are the same across all participants, disregarding the possibility of different features across participants which is captured in Vertical Federated Learning (VFL). To close this gap in the literature, we propose a novel method VFL-RPS for participant selection in VFL, as a pre-training step. We have tested our method on several data sets performing both regression and classification tasks, showing that our method leads to comparable results as using all data by only selecting a few participants. In addition, we show that our method outperforms existing methods for participant selection in VFL.