Open-Vocabulary Federated Learning with Multimodal Prototyping

arXiv:2404.01232v1 Announce Type: cross
Abstract: Existing federated learning (FL) studies usually assume the training label space and test label space are identical. However, in real-world applications, this assumption is too ideal to be true. A new user could come up with queries that involve data from unseen classes, and such open-vocabulary queries would directly defect such FL systems. Therefore, in this work, we explicitly focus on the under-explored open-vocabulary challenge in FL. That is, for a new user, the global …

abstract applications arxiv cs.cl cs.cv data federated learning however multimodal prototyping queries space studies test training true type world