In many spatial trajectory-based applications, it is necessary to map raw trajectory data points onto road networks in digital maps, which is commonly referred to as a map-matching process. While most previous map-matching methods have focused on using rule-based algorithms to deal with the map-matching problems, in this paper, we consider the map-matching task from the data-driven perspective, proposing a deep learning-based map-matching model. We build a Transformer-based map-matching model with a transfer learning approach. We generate trajectory data to pre-train the Transformer model and then fine-tune the model with a limited number of ground-truth data to minimize the model development cost and reduce the real-to-virtual gap. Three metrics (Average Hamming Distance, F-score, and BLEU) at two levels (point and segment level) are used to evaluate the model performance. The results indicate that the proposed model outperforms existing models. Furthermore, we use the attention weights of the Transformer to plot the map-matching process and find how the model matches the road segments correctly.
Multilingual Transformers for Product Matching -- Experiments and a New Benchmark in Polish
Warsaw University of Technology(华沙理工大学);Systems Research Institute, Polish Academy of Sciences(波兰科学院系统研究所);AGH University of Science and Technology(AGH科技大学)
产品匹配对应于跨不同数据源匹配相同产品的任务。它通常采用可用的产品特征,除了是多模态的,即,由各种数据类型组成,可能是非同质的和不完整的。本文表明,预训练,多语言Transformer模型,微调后,适合解决产品匹配问题,使用文本功能在英语和波兰语。我们在Web Data Commons上用英语测试了多语言mBERT和XLM-RoBERTa模型-这是训练数据集和大规模产品匹配的黄金标准。所获得的结果表明,这些模型的性能类似于在此集合上测试的最新解决方案,在某些情况下,结果甚至更好。此外,我们准备了一个新的数据集,完全在波兰和基于提供选定的类别从几个在线商店获得的研究目的。它是波兰语中第一个用于产品匹配任务的开放数据集,可以比较预训练模型的有效性。因此,我们还展示了在波兰数据集上通过微调mBERT和XLM-RoBERTa模型获得的基线结果。
Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network
School of Industrial and Systems Engineering, Georgia Tech(佐治亚理工学院工业与系统工程系);School of Electrical and Computer Engineering, Georgia Tech(佐治亚理工学院电气与计算机工程系)
本文提出了一种深度学习辅助综合方法,用于直接端到端生成具有3D EM结构的RF/mm波无源匹配网络。与现有的方法,从目标电路元件值和目标拓扑结构合成EM结构不同,我们所提出的方法实现了直接合成的无源网络给定的网络拓扑结构,从期望的性能值作为输入。我们展示了建议的合成神经网络(NN)模型上的片上1:1变压器为基础的阻抗匹配网络。通过利用参数共享,合成NN模型成功地从输入阻抗和负载电容器中提取相关特征,并预测45 nm SOI工艺中的Transformer 3D EM几何形状,其将标准50 $Ω$负载与目标输入阻抗匹配,同时吸收两个负载电容器。作为概念验证,合成了几个示例Transformer几何形状,并在Ansys HFSS中进行了验证,以提供所需的输入阻抗。
Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via Transformers
Skolkovo Institute of Science and Technology(斯克洛夫学院科学与技术研究所);Sberbank(储蓄银行);AI4S Center(AI4S中心);Artificial Intelligence Research Institute(人工智能研究 institute)