Picture for Ligang He

Ligang He

Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

Sep 14, 2021
Wentai Wu, Ligang He, Weiwei Lin

Figure 1 for Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

Figure 2 for Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

Figure 3 for Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

Figure 4 for Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

* 9 pages with appendix

Access Paper or Ask Questions

FedProf: Optimizing Federated Learning with Dynamic Data Profiling

Feb 02, 2021
Wentai Wu, Ligang He, Weiwei Lin, Rui Mao, Chenlin Huang, Wei Song

Figure 1 for FedProf: Optimizing Federated Learning with Dynamic Data Profiling

Figure 2 for FedProf: Optimizing Federated Learning with Dynamic Data Profiling

Figure 3 for FedProf: Optimizing Federated Learning with Dynamic Data Profiling

Figure 4 for FedProf: Optimizing Federated Learning with Dynamic Data Profiling

* 9 pages, 7 figures, intended for ICML'20

Access Paper or Ask Questions

An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

Nov 04, 2020
Tiansheng Huang, Weiwei Lin, Wentai Wu, Ligang He, Keqin Li, Albert Y. Zomaya

Figure 1 for An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

Figure 2 for An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

Figure 3 for An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

Figure 4 for An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

* Accepted by IEEE TPDS

Access Paper or Ask Questions

Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems

Jul 28, 2020
Wentai Wu, Ligang He, Weiwei Lin, Rui Mao

Figure 1 for Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems

Figure 2 for Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems

Figure 3 for Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems

Figure 4 for Accelerating Federated Learning over Reliability-Agnostic Clients in Mobile Edge Computing Systems

* 13 pages, 7 figures, with Appendix. Under review by IEEE TPDS

Access Paper or Ask Questions

SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead

Oct 03, 2019
Wentai Wu, Ligang He, Weiwei Lin, RuiMao, Stephen Jarvis

Figure 1 for SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead

Figure 2 for SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead

Figure 3 for SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead

Figure 4 for SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead

* 11 pages, 7 figures, 12 tables

Access Paper or Ask Questions