7 Papers
1 Citations
Feng Han is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Software bug. The author has an hindex of 1, co-authored 4 publications.
Chat about Author
Papers
Efficient Federated-Learning Model Debugging
Anran Li,Lan Zhang,Junhao Wang,Juntao Tan,Feng Han,Yaxuan Qin,Nikolaos M. Freris,Xiang-Yang Li +7 more
- 19 Apr 2021
TL;DR: Zhang et al. as discussed by the authors proposed FLDebugger, which traces the global model's test errors, jointly through the training log and the underlying learning algorithm, back to first identify the clients and subsequently their training samples that are most responsible for the errors.
42
Scape: Scalable Collaborative Analytics System on Private Database with Malicious Security
Feng Han,Liang Zhang,Hanwen Feng,Weiran Liu,Xiangyang Liy +4 more
- 01 May 2022
TL;DR: The general join protocol has O (n log2 n + m) communication/computation cost when joining two tables with o (n) rows to a table with 0 (m) rows, significantly outperforming the state-of-the-art approach with O(n2) cost.
15
SHAD: Privacy-Friendly Shared Activity Detection and Data Sharing
Feng Han,Lan Zhang,Xuanke You,Guangjing Wang,Xiang-Yang Li +4 more
- 01 Nov 2019
TL;DR: A novel system SHAD is proposed to achieve privacy-friendly shared activity detection and multimedia data auto-sharing based on users' historical multimodal data and an activity-semantic graph is designed, which protects both raw data and semantic information of data.
4
Poster: Cross Labelling and Learning Unknown Activities Among Multimodal Sensing Data
Lan Zhang,Daren Zheng,Zhengtao Wu,Mengjing Liu,Mu Yuan,Feng Han,Xiang-Yang Li +6 more
- 11 Oct 2019
TL;DR: This work proposes MultiSense, a paradigm for automatically mining potential perception, cross-labelling each modal data, and then improving the learning models over the set of multimodal data and demonstrates that MultiSense significantly improves the data usability and the power of theLearning models.
1
Towards Privacy-Preserving Speech Data Publishing
Jianwei Qian,Feng Han,Jiahui Hou,Chunhong Zhang,Yu Wang,Xiang-Yang Li +5 more
- 16 Apr 2018
TL;DR: A heuristic algorithm is proposed to personalize the sanitization for speakers to restrict their privacy leak (p-leak limit) while minimizing the utility loss, and a novel method - key term perturbation for speech contentsanitization is designed.