no code implementations • 21 May 2021 • Ze Meng, Jinnian Zhang, Yumeng Li, Jiancheng Li, Tanchao Zhu, Lifeng Sun
Modeling powerful interactions is a critical challenge in Click-through rate (CTR) prediction, which is one of the most typical machine learning tasks in personalized advertising and recommender systems.
2 code implementations • 26 May 2020 • Xin Yao, Lifeng Sun
Federated learning (FL) refers to the learning paradigm that trains machine learning models directly in the decentralized systems consisting of smart edge devices without transmitting the raw data, which avoids the heavy communication costs and privacy concerns.
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.
1 code implementation • CVPR 2014 • Kang Zhang, Yuqiang Fang, Dongbo Min, Lifeng Sun, Shiqiang Yang. Shuicheng Yan, Qi Tian
We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels.
1 code implementation • 10 Feb 2014 • Kang Zhang, Jiyang Li, Yijing Li, Weidong Hu, Lifeng Sun, Shiqiang Yang
In this paper, we propose a novel binary-based cost computation and aggregation approach for stereo matching problem.