在许多数据挖掘和机器学习任务(包括降低维度降低,离群检测,相似性搜索和子空间群集)中,对内在维度(ID)的准确估计至关重要。但是,由于它们的收敛性通常需要数百个点的样本量(即邻域尺寸),因此现有的ID估计方法可能仅对数据组成的应用程序组成的应用程序有限。在本文中,我们提出了一个局部ID估计策略,即使对于“紧密”的地方,稳定的策略也只有20个样本。估计器基于最新的固有维度(局部固有维度(LID))的极端价值理论模型,在样品成员之间的所有可用成对距离上应用MLE技术。我们的实验结果表明,我们提出的估计技术可以实现明显更小的方差,同时保持可比的偏见水平,而样本量比最先进的估计器小得多。
translated by 谷歌翻译
Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node's representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture -jumping knowledge (JK) networks -that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.
translated by 谷歌翻译
Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction.
translated by 谷歌翻译
这项工作与发现物理系统的偏微分方程(PDE)有关。现有方法证明了有限观察结果的PDE识别,但未能保持令人满意的噪声性能,部分原因是由于次优估计衍生物并发现了PDE系数。我们通过引入噪音吸引物理学的机器学习(NPIML)框架来解决问题,以在任意分布后从数据中发现管理PDE。我们的建议是双重的。首先,我们提出了几个神经网络,即求解器和预选者,这些神经网络对隐藏的物理约束产生了可解释的神经表示。在经过联合训练之后,求解器网络将近似潜在的候选物,例如部分衍生物,然后将其馈送到稀疏的回归算法中,该算法最初公布了最有可能的PERSIMISIAL PDE,根据信息标准决定。其次,我们提出了基于离散的傅立叶变换(DFT)的Denoising物理信息信息网络(DPINNS),以提供一组最佳的鉴定PDE系数,以符合降低降噪变量。 Denoising Pinns的结构被划分为前沿投影网络和PINN,以前学到的求解器初始化。我们对五个规范PDE的广泛实验确认,该拟议框架为PDE发现提供了一种可靠,可解释的方法,适用于广泛的系统,可能会因噪声而复杂。
translated by 谷歌翻译
本文介绍了Hitachi团队的建议自动采样系统,为自动采样的第一个共享任务(Automin-2021)。我们利用可参考方法(即,不使用培训分钟)进行自动采样(任务A),首先将转录成块分成块,随后将这些块与精细调整的预先训练的BART模型总结一下论聊天对话的概述语料库。此外,我们将参数挖掘技术应用于生成的分钟,以一种结构良好和连贯的方式重新组织它们。我们利用多个相关性分数来确定在给出的转录物或另一分钟时是否从相同的会议中衍生出一分钟(任务B和C)。在这些分数之上,我们培养传统的机器学习模型来绑定它们并进行最终决策。因此,我们的任务方法是在语法正确和流畅性方面,在所有提交的所有提交和最佳系统中实现最佳充分性评分。对于任务B和C,所提出的模型成功地表现了大多数投票基线。
translated by 谷歌翻译