no code implementations • 9 Aug 2023 • Zijian Li, Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang
For better privacy preservation, we propose a hard feature augmentation method to transfer real features towards the decision boundary, with which the synthetic data not only improve the model generalization but also erase the information of real features.
1 code implementation • 25 May 2023 • Jiahao Tan, Yipeng Zhou, Gang Liu, Jessie Hui Wang, Shui Yu
More specifically, we decouple a NN model into a personalized feature extractor, obtained by aggregating models from similar clients, and a classifier, which is obtained by local training and used to estimate client similarity.
no code implementations • 11 Jun 2022 • Zijian Li, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang
A combination of the local private dataset and synthetic dataset with confident pseudo labels leads to nearly identical data distributions among clients, which improves the consistency among local models and benefits the global aggregation.
no code implementations • 20 Dec 2021 • Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang
By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated learning.
no code implementations • 20 Dec 2021 • Xuanjie Li, Yuedong Xu, Jessie Hui Wang, Xin Wang, John C. S. Lui
By transforming our decentralized algorithm into a centralized inexact proximal gradient algorithm with variance reduction, and controlling the bounds of error sequences, we prove that DPSVRG converges at the rate of $O(1/T)$ for general convex objectives plus a non-smooth term with $T$ as the number of iterations, while DSPG converges at the rate $O(\frac{1}{\sqrt{T}})$.
no code implementations • 26 Apr 2021 • Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang
Federated edge learning (FEEL) has emerged as an effective approach to reduce the large communication latency in Cloud-based machine learning solutions, while preserving data privacy.
no code implementations • 28 Jan 2020 • Jialin Dong, Jun Zhang, Yuanming Shi, Jessie Hui Wang
In this paper, we develop multi-armed bandit approaches for more efficient detection via coordinate descent, which make a delicate trade-off between exploration and exploitation in coordinate selection.