Adapting LLMs for Efficient Context Processing through Soft Prompt Compression

no code implementations • 7 Apr 2024 • Cangqing Wang, Yutian Yang, Ruisi Li, Dan Sun, Ruicong Cai, Yuzhu Zhang, Chengqian Fu, Lillian Floyd

By amalgamating soft prompt compression with sophisticated summarization, SoftPromptComp confronts the dual challenges of managing lengthy contexts and ensuring model scalability.

Text Generation

Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning

no code implementations • 29 Apr 2023 • Yan Kang, Hanlin Gu, Xingxing Tang, Yuanqin He, Yuzhu Zhang, Jinnan He, Yuxing Han, Lixin Fan, Kai Chen, Qiang Yang

Different from existing CMOFL works focusing on utility, efficiency, fairness, and robustness, we consider optimizing privacy leakage along with utility loss and training cost, the three primary objectives of a TFL system.

Fairness Federated Learning