S
Shaofeng Cai
Researcher at National University of Singapore
Publications - 24
Citations - 468
Shaofeng Cai is an academic researcher from National University of Singapore. The author has contributed to research in topics: Deep learning & Interpretability. The author has an hindex of 8, co-authored 21 publications receiving 182 citations.
Papers
More filters
Journal ArticleDOI
Privacy Preserving Vertical Federated Learning for Tree-based Models
TL;DR: This paper proposes Pivot, a novel solution for privacy preserving vertical decision tree training and prediction, ensuring that no intermediate information is disclosed other than those the clients have agreed to release (i.e., the final tree model and the prediction output).
Proceedings Article
Understanding Architectures Learnt by Cell-based Neural Architecture Search
Yao Shu,Wei Wang,Shaofeng Cai +2 more
TL;DR: It is uncovered that the architectures generated by NAS algorithms share a common connection pattern, which contributes to their fast convergence, and it is empirically and theoretically shown that the fast convergence is the consequence of smooth loss landscape and accurate gradient information conducted by the common connectionpattern.
Journal ArticleDOI
Privacy preserving vertical federated learning for tree-based models
TL;DR: Pivot as discussed by the authors is a solution for privacy preserving vertical decision tree training and prediction, ensuring that no intermediate information is disclosed other than those the clients have agreed to release (i.e., the final tree model and the prediction output).
Posted Content
Effective and Efficient Dropout for Deep Convolutional Neural Networks.
TL;DR: The order of the dropout operations are proposed to be adjusted to address the conflict between the conventional dropout and the batch normalization operation after it, and other structurally more suited dropout variants are examined and introduced for more efficient and effective regularization for CNNs.
Journal ArticleDOI
The Disruptions of 5G on Data-Driven Technologies and Applications
Dumitrel Loghin,Shaofeng Cai,Gang Chen,Tien Tuan Anh Dinh,Feiyi Fan,Qian Lin,Janice Ng,Beng Chin Ooi,Xutao Sun,Quang-Trung Ta,Wei Wang,Xiaokui Xiao,Yang Yang,Meihui Zhang,Zhonghua Zhang +14 more
TL;DR: In this paper, the authors analyze the impact of 5G on both traditional and emerging technologies and project their view on future research challenges and opportunities, and investigate how 5G can help the development of federated learning.