2.4k citations
- Zhejiang UniversityCN121 papers
- Alibaba Group (United States)US60 papers
- Tsinghua UniversityCN52 papers
- Peking UniversityCN50 papers
- University of Science and Technology of ChinaCN50 papers
- Nanyang Technological UniversitySG42 papers
- Chinese Academy of SciencesCN37 papers
- Shanghai Jiao Tong UniversityCN34 papers
- University of Chinese Academy of SciencesCN26 papers
- University of Electronic Science and Technology of ChinaCN19 papers
- Fudan UniversityCN18 papers
- Hong Kong University of Science and TechnologyHK17 papers
15 papers · 1 filter
Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability
Yikai Yan, Chaoyue Niu, Yucheng Ding +5
Federated learning is a new distributed machine learning framework, where a bunch of heterogeneous clients collaboratively train a model without sharing training data. In this work…
Learning to Advertise for Organic Traffic Maximization in E-Commerce Product Feeds
Dagui Chen, Junqi Jin, Weinan Zhang +7
Most e-commerce product feeds provide blended results of advertised products and recommended products to consumers. The underlying advertising and recommendation platforms share si…
ASAP: Architecture Search, Anneal and Prune
Asaf Noy, Niv Nayman, Tal Ridnik +5
Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models. Yet, their main drawback is the computational complexity of the s…
Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
Yuchi Zhang, Yongliang Wang, Liping Zhang +2
Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. Ho…
Stagewise Training Accelerates Convergence of Testing Error Over SGD
Zhuoning Yuan, Yan Yan, Rong Jin +1
Stagewise training strategy is widely used for learning neural networks, which runs a stochastic algorithm (e.g., SGD) starting with a relatively large step size (aka learning rate…
Deep Interest Evolution Network for Click-Through Rate Prediction
Guorui Zhou, Na Mou, Ying Fan +5
Click-through rate~(CTR) prediction, whose goal is to estimate the probability of the user clicks, has become one of the core tasks in advertising systems. For CTR prediction model…