GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation
GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation
复制标题
GOF-TTE：用于行程时间估计的生成在线联合学习框架
DOI：
10.1109/jiot.2022.3190864
复制
发表时间：
2022
影响因子：
10.6
通讯作者：
Shibasaki Ryosuke
中科院分区：
文献类型：
--
作者：
Zhang Zhiwen;Wang Hongjun;Fan Zipei;Chen Jiyuan;Song Xuan;Shibasaki Ryosuke
估计路径的旅行时间是智能交通系统的一个重要课题。它是交通监控、路线规划和出租车调度等实际应用的基础。然而，为这种数据驱动的任务构建模型需要大量用户的旅行信息，这些信息与他们的隐私密切相关，因此不太可能被共享。如果我们直接应用联邦学习，跨数据所有者的非独立同分布（Non-IID）轨迹数据也使得预测模型的个性化变得极具挑战性。最后，之前关于出行时间估计（TTE）的工作没有考虑道路的实时交通状态，我们认为这会显着影响预测。为了解决上述挑战，我们为移动用户群引入了GOF-TTE，即TTE的生成在线联邦学习框架，该框架1）利用联邦学习方法，允许在训练时将私有数据保留在客户端设备上，并将全局模型设计为所有客户端共享的在线生成模型，以推断实时道路交通状态；2）除了在服务器上共享基础模型外，还为每个客户端调整微调的个性化模型来研究他们的个人驾驶习惯，用于局部全局模型预测产生的残差。我们还对我们的框架采用了简单的隐私攻击，并实现了差分隐私机制，以进一步保证隐私安全。最后，我们在滴滴成都和西安的两个真实公共出租车数据集上进行了实验。实验结果证明了我们提出的框架的有效性。
Estimating the travel time of a path is an essential topic for the intelligent transportation system. It serves as the foundation for real-world applications, such as traffic monitoring, route planning, and taxi dispatching. However, building a model for such a data-driven task requires a large amount of users’ travel information, which closely relates to their privacy and, thus, is less likely to be shared. The not independent and identically distributed (Non-IID) trajectory data across data owners also make a predictive model extremely challenging to be personalized if we directly apply federated learning. Finally, previous work on travel time estimation (TTE) does not consider the real-time traffic state of roads, which we argue, can significantly influence the prediction. To address the above challenges, we introduce GOF-TTE for the mobile user group, generative online federated learning framework for TTE, which 1) utilizes the federated learning approach, allowing private data to be kept on client devices while training, and designs the global model as an online generative model shared by all clients to infer the real-time road traffic state and 2) apart from sharing a base model at the server, adapts a fine-tuned personalized model for every client to study their personal driving habits, making up for the residual error made by localized global model prediction. We also employ a simple privacy attack to our framework and implement the differential privacy mechanism to guarantee privacy safety further. Finally, we conduct experiments on two real-world public taxi data sets of DiDi Chengdu and Xi’an. The experimental results demonstrate the effectiveness of our proposed framework.
DOI：
--
发表时间：
2020-03
期刊：
ArXiv
影响因子：
--
作者：
Jonas Geiping;Hartmut Bauermeister;Hannah Dröge;Michael Moeller
通讯作者：
Jonas Geiping;Hartmut Bauermeister;Hannah Dröge;Michael Moeller
“与组方案相关的角色产品和平衡集”（预印本）。
DOI：
--
发表时间：
--
期刊：
影响因子：
--
作者：
通讯作者：
--
观点：学习分享。
影响因子：
64.8
作者：
Quackenbush,John
通讯作者：
Quackenbush,John