Road networks are a type of spatial network, where edges may be associated with qualitative information such as road type and speed limit. Unfortunately, such information is often incomplete; for instance, OpenStreetMap only has speed limits for 13% of all Danish road segments. This is problematic for analysis tasks that rely on such information for machine learning. To enable machine learning in such circumstances, one may consider the application of network embedding methods to extract structural information from the network. However, these methods have so far mostly been used in the context of social networks, which differ significantly from road networks in terms of, e.g., node degree and level of homophily (which are key to the performance of many network embedding methods). We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in road networks. Due to the often limited availability of information on other relevant road characteristics, the analysis focuses on leveraging the spatial network structure. Our results suggest that network embedding methods can indeed be used for deriving relevant network features (that may, e.g, be used for predicting speed limits), but that the qualities of the embeddings differ from embeddings for social networks.
Road Network Metric Learning for Estimated Time of Arrival
Tsinghua University(清华大学);DiDi AI Labs(滴滴人工智能实验室)
近年来,深度学习在估计到达时间(Estimated Time of Arrival,ETA)方面取得了可喜的成果,ETA被认为是预测沿给定路径从起点到目的地的行程时间,其中一个关键技术是使用嵌入向量来表示道路网络的元素,如路段(路段)。然而,嵌入存在数据稀疏性问题,即使在Uber和DiDi等大型乘车平台中,道路网络中的许多链接也只有很少的浮动汽车经过。数据不足会使嵌入向量处于欠拟合状态,影响ETA预测的准确性。为了解决数据稀疏性问题,我们提出了道路网络度量学习框架ETA(RNML-ETA)。它由两部分组成:(1)预测行进时间的主回归任务,以及(2)改进链路嵌入向量的质量的辅助度量学习任务。我们进一步提出了三角损失,一个新的损失函数,以提高度量学习的效率。我们在大规模真实世界数据集上验证了RNML-ETA的有效性,表明我们的方法优于最先进的模型,并且推广集中在数据较少的冷链接上。
Hybrid Graph Embedding Techniques in Estimated Time of Arrival Task
Sberbank(俄罗斯联邦储蓄银行);National University of Science and Technology ``MISIS''(国立科技研究大学“莫斯科国立钢铁合金学院”);Artificial Intelligence Research Institute (AIRI)(人工智能研究院(AIRI))
Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
School of Computer Science and Engineering, Sun Yat-Sen University, China(中山大学计算机科学与工程学院);School of Artificial Intelligence, Sun Yat-Sen University, China(中山大学人工智能学院);Guangdong Key Laboratory of Big Data Analysis and Processing, China(广东大数据分析与处理重点实验室)
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
University of Lübeck(吕贝克大学);Hochschule Anhalt(安哈尔特应用技术大学);Continental AG(大陆集团);University of Liverpool(利物浦大学);University of Wuppertal(伍珀塔尔大学);Technical University of Munich(慕尼黑工业大学)
Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integration
School of Software, Liaoning Technical University(软件学院,辽宁技术大学);Faculty of Electronic and Information Engineering, Liaoning Technical University(电子与信息工程学院,辽宁技术大学)