Spatio-temporal modeling as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the underlying heterogeneity and non-stationarity implied in the graph streams, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a large-scale spatio-temporal dataset that contains a variaty of non-stationary phenomena. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle locations and time slots with different patterns and be robustly adaptive to different anomalous situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a new large-scale traffic speed dataset in which traffic incident information is contained. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle the road links and time slots with different patterns and be robustly adaptive to any anomalous traffic situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

尽管与以太坊这样的加密货币交易变得越来越普遍，但欺诈和其他犯罪交易并不少见。图分析算法和机器学习技术检测到导致大型交易网络网络钓鱼的可疑交易。已经提出了许多图形神经网络（GNN）模型将深度学习技术应用于图形结构。尽管在以太坊交易网络中使用GNN模型进行了网络钓鱼检测的研究，但尚未研究针对顶点和边缘数量的规模以及标签不平衡的模型。在本文中，我们比较了GNN模型在实际以太坊交易网络数据集和网络钓鱼报告的标签数据上的模型性能，以详尽地比较和验证哪些GNN模型和超参数产生最佳精度。具体而言，我们评估了代表性同质GNN模型的模型性能，该模型考虑了单型节点和边缘以及支持不同类型的节点和边缘的异质GNN模型。我们表明，异质模型比同质模型具有更好的模型性能。特别是，RGCN模型在整体指标中取得了最佳性能。

最新提出的基于变压器的图形模型的作品证明了香草变压器用于图形表示学习的不足。要了解这种不足，需要研究变压器的光谱分析是否会揭示其对其表现力的见解。类似的研究已经确定，图神经网络（GNN）的光谱分析为其表现力提供了额外的观点。在这项工作中，我们系统地研究并建立了变压器领域中的空间和光谱域之间的联系。我们进一步提供了理论分析，并证明了变压器中的空间注意机制无法有效捕获所需的频率响应，因此，固有地限制了其在光谱空间中的表现力。因此，我们提出了feta，该框架旨在在整个图形频谱（即图形的实际频率成分）上进行注意力类似于空间空间中的注意力。经验结果表明，FETA在标准基准的所有任务中为香草变压器提供均匀的性能增益，并且可以轻松地扩展到具有低通特性的基于GNN的模型（例如GAT）。

在在线广告中，可以通过某个拍卖系统对一系列潜在的广告进行排名，其中通常会在广告领域中选择和展示Top-1广告。在本文中，我们显示了拍卖系统中存在的选择偏差问题。我们分析选择偏见破坏了拍卖的真实性，这意味着拍卖中的买家（广告商）无法最大化其利润。尽管选择偏见在统计领域是众所周知的，并且有很多研究，但我们的主要贡献是将偏见的理论分析与拍卖机制相结合。在使用在线A/B测试的实验中，我们评估了拍卖系统上的选择偏差，该拍卖系统的排名得分是预测的CTR（单击率）广告的函数。该实验表明，通过使用多任务学习来学习所有广告的数据，可以大大降低选择偏差。