no code implementations • 24 Oct 2019 • Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun
Extensive experiments in several typical lifelong learning scenarios demonstrate that our method outperforms the state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks.
no code implementations • 18 Oct 2019 • Xin Yao, Tianchi Huang, Rui-Xiao Zhang, Ruiyu Li, Lifeng Sun
Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices.
2 code implementations • 16 Aug 2019 • Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun
Federated learning (FL) enables on-device training over distributed networks consisting of a massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) devices.
1 code implementation • 6 Aug 2019 • Tianchi Huang, Chao Zhou, Rui-Xiao Zhang, Chenglei Wu, Xin Yao, Lifeng Sun
Using trace-driven and real-world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required.