Dual Prompt Tuning for Domain-Aware Federated Learning

arXiv:2310.03103v4 Announce Type: replace
Abstract: Federated learning is a distributed machine learning paradigm that allows multiple clients to collaboratively train a shared model with their local data. Nonetheless, conventional federated learning algorithms often struggle to generalize well due to the ubiquitous domain shift across clients. In this work, we consider a challenging yet realistic federated learning scenario where the training data of each client originates from different domains. We address the challenges of domain shift by leveraging the technique of …

abstract algorithms arxiv cs.lg data distributed domain federated learning machine machine learning multiple paradigm prompt prompt tuning shift struggle train type work