FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction

Liu, Yinghao1; Fan, Zipei1; Song, Xuan2; Shibasaki, Ryosuke1

2021-12-01

10.3390/s21248282

SENSORS   影响因子和分区

1424-8220

The prediction of human mobility can facilitate resolving many kinds of urban problems, such as reducing traffic congestion, and promote commercial activities, such as targeted advertising. However, the requisite personal GPS data face privacy issues. Related organizations can only collect limited data and they experience difficulties in sharing them. These data are in "isolated islands" and cannot collectively contribute to improving the performance of applications. Thus, the method of federated learning (FL) can be adopted, in which multiple entities collaborate to train a collective model with their raw data stored locally and, therefore, not exchanged or transferred. However, to predict long-term human mobility, the performance and practicality would be impaired if only some models were simply combined with FL, due to the irregularity and complexity of long-term mobility data. Therefore, we explored the optimized construction method based on the high-efficient gradient-boosting decision tree (GBDT) model with FL and propose the novel federated voting (FedVoting) mechanism, which aggregates the ensemble of differential privacy (DP)-protected GBDTs by the multiple training, cross-validation and voting processes to generate the optimal model and can achieve both good performance and privacy protection. The experiments show the great accuracy in long-term predictions of special event attendance and point-of-interest visits. Compared with training the model independently for each silo (organization) and state-of-art baselines, the FedVoting method achieves a significant accuracy improvement, almost comparable to the centralized training, at a negligible expense of privacy exposure.

long-term human mobility prediction privacy protection federated learning gradient-boosting decision tree differential privacy GPS

SCI ; EI

英语

通讯

Japan's Ministry of Education, Culture, Sports, Science, and Technology (MEXT)[20K19782]

Chemistry ; Engineering ; Instruments & Instrumentation

Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation

WOS:000742102500001

MDPI

CHEMISTRY

Web of Science

1.Univ Tokyo, Ctr Spatial Informat Sci, Kashiwanoha 5 Chome 1-5, Kashiwa, Chiba 2770882, Japan
2.Southern Univ Sci & Technol SUSTech, SUSTech UTokyo Joint Res Ctr Super Smart City, Dept Comp Sci & Engn, Shenzhen 518055, Peoples R China

Liu, Yinghao,Fan, Zipei,Song, Xuan,et al. FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction[J]. SENSORS,2021,21(24).

Liu, Yinghao,Fan, Zipei,Song, Xuan,&Shibasaki, Ryosuke.(2021).FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction.SENSORS,21(24).

Liu, Yinghao,et al."FedVoting: A Cross-Silo Boosting Tree Construction Method for Privacy-Preserving Long-Term Human Mobility Prediction".SENSORS 21.24(2021).