TabVFL: Improving Latent Representation in Vertical Federated Learning

arXiv:2404.17990v1 Announce Type: new
Abstract: Autoencoders are popular neural networks that are able to compress high dimensional data to extract relevant latent information. TabNet is a state-of-the-art neural network model designed for tabular data that utilizes an autoencoder architecture for training. Vertical Federated Learning (VFL) is an emerging distributed machine learning paradigm that allows multiple parties to train a model collaboratively on vertically partitioned data while maintaining data privacy. The existing design of training autoencoders in VFL is to train …

abstract architecture art arxiv autoencoder autoencoders cs.dc cs.lg data distributed extract federated learning improving information machine machine learning network networks neural network neural networks paradigm popular representation state tabular tabular data training type