no code implementations • 16 Feb 2024 • Richeng Jin, Yujie Gu, Kai Yue, Xiaofan He, Zhaoyang Zhang, Huaiyu Dai
In this paper, we propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously.
no code implementations • 8 Jun 2022 • Kai Yue, Richeng Jin, Chau-Wai Wong, Dror Baron, Huaiyu Dai
Prior work has shown that the gradient sharing strategies in federated learning can be vulnerable to data reconstruction attacks.
no code implementations • 7 Oct 2021 • Kai Yue, Richeng Jin, Ryan Pilgrim, Chau-Wai Wong, Dror Baron, Huaiyu Dai
The paradigm addresses the challenge of statistical heterogeneity by transmitting update data that are more expressive than those of the conventional FL paradigms.
1 code implementation • 6 Oct 2021 • Kai Yue, Richeng Jin, Chau-Wai Wong, Huaiyu Dai
Federated learning allows collaborative workers to solve a machine learning problem while preserving data privacy.
1 code implementation • 2 Aug 2021 • Kai Yue, Richeng Jin, Chau-Wai Wong, Huaiyu Dai
In each communication round, we select the predictor and quantizer based on the rate-distortion cost, and further reduce the redundancy with entropy coding.
no code implementations • 29 Apr 2018 • Kai Yue, Lei Yang, Ruirui Li, Wei Hu, Fan Zhang, Wei Li
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.