浙江省城乡与住房建设厅网站,什么网站做的好看,cms管理,自己网站首页如何设置课程概要本课程来自集智学园图网络论文解读系列活动。是对论文《Graph WaveNet for Deep Spatial-Temporal Graph Modeling》的解读。时空图建模 (Spatial-temporal graph modeling)是分析系统中组成部分的空间维相关性和时间维趋势的重要手段。已有算法大多基于已知的固定的图… 课程概要本课程来自集智学园图网络论文解读系列活动。是对论文《Graph WaveNet for Deep Spatial-Temporal Graph Modeling》的解读。时空图建模 (Spatial-temporal graph modeling)是分析系统中组成部分的空间维相关性和时间维趋势的重要手段。已有算法大多基于已知的固定的图结构信息来获取空间相关性而邻接矩阵所包含的连接关系并不能反应真实的节点间交互。此外现有基于 RNN 和 CNN 的时域建模方式不能真正的捕捉其中所存在的长程相关。本文提出了一个新的图神经网络模型 Graph WaveNet 用于时空图建模。其中包括两个组件一个是自适应依赖矩阵(adaptive dependency matrix)通过节点嵌入进行训练用来精确建模节点的空间相关性。另一个是堆叠的 1D 带孔卷积(stacked dilated 1D convolution)增加了模型在时域的感受野的大小。通过两个交通流预测数据集的测试Graph WaveNet 均能达到 state-of-the-art 的效果。课程资料论文题目Graph WaveNet for Deep Spatial-Temporal Graph Modeling论文地址https://arxiv.org/abs/1906.00121 课程讲师王硕王硕2014年毕业于东北大学模式识别与智能系统专业2016年加入彩云天气负责雾霾预报算法及系统。论文原文摘要Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.课程大纲介绍了论文的基础信息和论文背景介绍了本篇论文解决的科学问题——时空序列预测分模块介绍了Graph WaveNet算法框架同时说明每个模块相关的以往研究介绍了对比模型以及实验结果展开相关的讨论探讨文章算法的局限性展示相关资源列表录播学习学习地址https://campus.swarma.org/play/coursedetail?id11091推荐学习集智图网络线上读书会公开招募图神经网络是深度学习领域的前沿热点议题尤其是图网络(GraphNetworks)提出以来深度学习有了实现因果推理的潜力。为了持续追踪相关领域的前沿进展集智俱乐部联合北师大系统科学学院张江课题组组织了以图网络为主题的线上读书会研讨最新论文孕育研究思路。每一期线上读书会由一位成员主讲形式为论文分享时间为每周一21:00-21:40。加入读书会群需报名审核原则上参与者应有能力独立完成一次线上分享。如果你也正在从事图网络与深度学习方面的研究工作或技术实践或者对该领域有强烈的学习意愿欢迎填写报名表申请加入“集智图网络论文分享小组”报名请扫下方小程序码填写报名表。填表之后会有入群方式。《产学结合自然语言处理及其应用》课程报名课程中讲解了自然语言处理的最新学术理论并联合学术界和工业界追踪最新进展与落地实践。课程由李嫣然、尹相志、小米科技相关技术负责人崔建伟和魏晨、彩云科技NLP算法工程师侯月源合力打造了 12 节课程涉及语言模型、机器翻译、情感分析、文本理解、知识图谱、文本生成六大主题。报名方式点击立即报名https://campus.swarma.org/play/coursedetail?id11076集智学园公众号swarmAI集智学园QQ群426390994集智学园官网campus.swarma.org商务合作投稿转载swarmaswarma.org
