Prioritizing Informative Features and Examples for Deep Learning from Noisy Data
D Park - arXiv preprint arXiv:2403.00013, 2024 - arxiv.org
In this dissertation, we propose a systemic framework that prioritizes informative features
and examples to enhance each stage of the development process. Specifically, we prioritize …
and examples to enhance each stage of the development process. Specifically, we prioritize …
Toward an accurate mobility trajectory recovery using contrastive learning
Y Liu, Y Chen, J Zhang, Y Xiao, X Wang - Frontiers of Information …, 2024 - Springer
Human mobility trajectories are fundamental resources for analyzing mobile behaviors in
urban computing applications. However, these trajectories, typically collected from location …
urban computing applications. However, these trajectories, typically collected from location …
基于对比学习的移动轨迹准确恢复
Y LIU, Y CHEN, J ZHANG, Y XIAO, X WANG, AY LIU… - Frontiers, 2024 - jzus.zju.edu.cn
在城市计算应用中, 用户轨迹数据是用户移动行为分析的基础数据源. 然而,
由于这些用户轨迹数据部分是从基于位置的服务中收集的, 在时间上常常具有稀疏性和不规则性 …
由于这些用户轨迹数据部分是从基于位置的服务中收集的, 在时间上常常具有稀疏性和不规则性 …