Abstract

Due to increasing concerns and regulations about data privacy (eg, General Data Protection Regulation), coupled with the growing computational power of edge devices, emerging data from realistic users have become much more fragmented, forming distributed private datasets across different clients (ie, organizations or personal devices). Respecting users’ privacy and restricted by these regulations, we have to assume that users’ data in a client are not allowed to transfer to a centralized server or other clients. For example, a hospital does not want to share its private data (eg, conversations, questions asked on its website/app) with other hospitals. This is despite the fact that models trained by a centralized dataset (ie, combining data from all clients) usually enjoy better performance on downstream tasks (eg, dialogue, question answering). Therefore, it is of vital importance to study NLP problems in such a …

Date

January 1, 1970

Authors

Bill Yuchen Lin, Chaoyang He, Chulin Xie, Fatemehsadat Mireshghallah, Ninareh Mehrabi, Tian Li, Mahdi Soltanolkotabi, Xiang Ren

Conference

Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)