1 code implementation • 14 Dec 2023 • Liping Yi, Han Yu, Zhuan Shi, Gang Wang, Xiaoguang Liu, Lizhen Cui, Xiaoxiao Li
Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs.
no code implementations • 20 Jul 2023 • Yuxin Shi, Zelei Liu, Zhuan Shi, Han Yu
By not using threshold-based reputation filtering, it provides FL clients with opportunities to redeem their reputations after a perceived poor performance, thereby further enhancing fair client treatment.
3 code implementations • 23 Mar 2023 • Liping Yi, Gang Wang, Xiaoguang Liu, Zhuan Shi, Han Yu
It is a communication and computation-efficient model-heterogeneous FL framework which trains a shared generalized global prediction header with representations extracted by heterogeneous extractors for clients' models at the FL server.
no code implementations • 28 Dec 2022 • Shipeng Wang, Qingzhong Li, Lizhen Cui, Zhongmin Yan, Yonghui Xu, Zhuan Shi, Xinping Min, Zhiqi Shen, Han Yu
Crowdsourcing, in which human intelligence and productivity is dynamically mobilized to tackle tasks too complex for automation alone to handle, has grown to be an important research topic and inspired new businesses (e. g., Uber, Airbnb).