Fed-TDA: Federated Tabular Data Augmentation on Non-IID Data. (arXiv:2211.13116v1 [cs.LG])

Non-independent and identically distributed (non-IID) data is a key challenge
in federated learning (FL), which usually hampers the optimization convergence
and the performance of FL. Existing data augmentation methods based on
federated generative models or raw data sharing strategies for solving the
non-IID problem still suffer from low performance, privacy protection concerns,
and high communication overhead in decentralized tabular data. To tackle these
challenges, we propose a federated tabular data augmentation method, named
Fed-TDA. The core idea of Fed-TDA is …

data fed non