Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in frequency domains (e.g., Fourier domain, wavelet domain), given that seasonal patterns can be better captured in these domains. In this work, we seek to understand the relationships between attention models in different time and frequency domains. Theoretically, we show that attention models in different domains are equivalent under linear conditions (i.e., linear kernel to attention scores). Empirically, we analyze how attention models of different domains show different behaviors through various synthetic experiments with seasonality, trend and noise, with emphasis on the role of softmax operation therein. Both these theoretical and empirical analyses motivate us to propose a new method: TDformer (Trend Decomposition Transformer), that first applies seasonal-trend decomposition, and then additively combines an MLP which predicts the trend component with Fourier attention which predicts the seasonal component to obtain the final prediction. Extensive experiments on benchmark time-series forecasting datasets demonstrate that TDformer achieves state-of-the-art performance against existing attention-based models.
translated by 谷歌翻译
Boundary conditions (BCs) are important groups of physics-enforced constraints that are necessary for solutions of Partial Differential Equations (PDEs) to satisfy at specific spatial locations. These constraints carry important physical meaning, and guarantee the existence and the uniqueness of the PDE solution. Current neural-network based approaches that aim to solve PDEs rely only on training data to help the model learn BCs implicitly. There is no guarantee of BC satisfaction by these models during evaluation. In this work, we propose Boundary enforcing Operator Network (BOON) that enables the BC satisfaction of neural operators by making structural changes to the operator kernel. We provide our refinement procedure, and demonstrate the satisfaction of physics-based BCs, e.g. Dirichlet, Neumann, and periodic by the solutions obtained by BOON. Numerical experiments based on multiple PDEs with a wide variety of applications indicate that the proposed approach ensures satisfaction of BCs, and leads to more accurate solutions over the entire domain. The proposed correction method exhibits a (2X-20X) improvement over a given operator model in relative $L^2$ error (0.000084 relative $L^2$ error for Burgers' equation).
translated by 谷歌翻译
我们考虑使用图形结构的概率预测问题,顶点的动态取决于其本地连接结构。我们提出了Gopher,一种方法,该方法将图形神经网络的感应偏差与神经杂物核对捕获了我们概率预测的内在局部连续动态。通过与基线模型进行比较,我们研究了这两个归纳偏差的好处,从而有助于解开每个益处的基线模型。我们发现,捕获图形结构对于准确的域概率预测和更具样本的高效模型至关重要。令人惊讶的是,我们的实验表明,尽管反映了真正的概率动态,但连续时间进化电感偏差很少没有利益。
translated by 谷歌翻译
定量回归是一种有效的技术,可以量化不确定性,符合挑战的潜在分布,并且通常通过在多个分位数水平上的联合学习提供完全概率预测。然而,这些关节分位数回归的常见缺点是\ textit {stantile交叉},其违反了条件分位式函数的理想单调属性。在这项工作中,我们提出了增量(样条曲线)量子函数I(S)QF,灵活和有效的无分布定量位估计框架,其解决了与简单的神经网络层的定量交叉。此外,I(s)QF Inter /外推预测与底层训练不同的任意定量水平。配备了对I(S)QF表示的连续排名概率得分的分析评估,我们将方法应用于基于NN的时间系列预测案例,其中尤其是昂达训练的分位数的昂贵重新培训成本的节省重大。我们还提供了在序列到序列设置下我们提出的方法的泛化误差分析。最后,广泛的实验证明了在其他基线上提高了一致性和准确性误差。
translated by 谷歌翻译
最近,深度神经网络在时间序列的预测中越来越受欢迎。他们成功的主要原因是他们有效捕获多个相关时间序列的复杂时间动态的能力。这些深度预测者的优势才开始在有足够数量的数据的情况下开始出现。这对实践中的典型预测问题提出了挑战,在实践中,每个时间序列的时间序列或观察值有限,或者两者兼而有之。为了应对这些数据稀缺问题,我们提出了一个新颖的域适应框架,域适应预报员(DAF)。 DAF利用具有丰富数据样本(源)的相关领域的统计强度,以通过有限的数据(目标)提高感兴趣域的性能。特别是,我们使用基于注意力的共享模块,该模块与跨域跨域和私人模块的域歧视器一起使用。我们同时诱导域不变的潜在特征(查询和密钥)和重新培训特定特征(值),以使源和目标域上的预报员的联合训练。一个主要的见解是,我们对齐密钥的设计使目标域即使具有不同的特征也可以利用源时间序列。对各个领域的广泛实验表明,我们提出的方法在合成和现实世界数据集上优于最先进的基准,而消融研究验证了我们的设计选择的有效性。
translated by 谷歌翻译
基于预测方法的深度学习已成为时间序列预测或预测的许多应用中的首选方法,通常通常优于其他方法。因此,在过去的几年中,这些方法现在在大规模的工业预测应用中无处不在,并且一直在预测竞赛(例如M4和M5)中排名最佳。这种实践上的成功进一步提高了学术兴趣,以理解和改善深厚的预测方法。在本文中,我们提供了该领域的介绍和概述:我们为深入预测的重要构建块提出了一定深度的深入预测;随后,我们使用这些构建块,调查了最近的深度预测文献的广度。
translated by 谷歌翻译
We introduce a challenging decision-making task that we call active acquisition for multimodal temporal data (A2MT). In many real-world scenarios, input features are not readily available at test time and must instead be acquired at significant cost. With A2MT, we aim to learn agents that actively select which modalities of an input to acquire, trading off acquisition cost and predictive performance. A2MT extends a previous task called active feature acquisition to temporal decision making about high-dimensional inputs. Further, we propose a method based on the Perceiver IO architecture to address A2MT in practice. Our agents are able to solve a novel synthetic scenario requiring practically relevant cross-modal reasoning skills. On two large-scale, real-world datasets, Kinetics-700 and AudioSet, our agents successfully learn cost-reactive acquisition behavior. However, an ablation reveals they are unable to learn to learn adaptive acquisition strategies, emphasizing the difficulty of the task even for state-of-the-art models. Applications of A2MT may be impactful in domains like medicine, robotics, or finance, where modalities differ in acquisition cost and informativeness.
translated by 谷歌翻译
解释性学者通过手动采样文档,应用代码以及将代码精炼和整理成类别,直到出现有意义的主题,从而从文本语料库中产生知识。鉴于大量的语料库,机器学习可以帮助扩展此数据采样和分析,但先前的研究表明,专家通常关注算法可能破坏或推动解释性奖学金。我们采用以人为本的设计方法来解决围绕机器辅助解释性研究的关注,以构建学术研究,该研究将机器中的集群算法纳入了脚手架解释性文本分析。随着学者将代码应用于文档和完善它们,所得编码的模式用作结构化元数据,该元数据限制了从语料库推断出的层次文档和单词簇。这些集群的交互式可视化可以帮助学者们战略性地对文档进行进一步的洞察力进行洞察力。 Scholastic证明了采用熟悉隐喻的以人为中心的算法设计和可视化如何通过交互式主题建模和文档群集来支持归纳和解释性研究方法。
translated by 谷歌翻译
本文讨论了创建和分析用于数据挖掘和文本分析研究的新数据集,这为利兹大学国家方言语料库的联合研究项目做出了贡献。该报告调查了机器学习分类器,以对各个法语国家的法语方言文本进行分类。遵循CRISP-DM方法的步骤,本报告探讨了数据收集过程,数据质量问题和数据转换以进行文本分析。最后,在应用了合适的数据挖掘技术之后,讨论了评估方法,最佳总体特征以及分类器和结论。
translated by 谷歌翻译
近年来,人类面孔的影子化化身已经走了很长一段路,但是该地区的研究受到缺乏公开可用的高质量数据集的限制。在这项工作中,我们介绍了Multiface,这是一种新的多视图,高分辨率的人脸数据集,该数据集是从13个身份的神经面部渲染研究中收集的13个身份。我们介绍了Mugsy,这是一种大型多摄像机设备,可捕获面部表现的高分辨率同步视频。 Multiface的目的是缩小学术界高质量数据的可访问性的差距,并使VR触觉研究能够进行研究。随着数据集的释放,我们对不同模型体系结构对模型的新观点和表达式的插值能力进行消融研究。通过有条件的VAE模型作为我们的基线,我们发现添加空间偏见,纹理翘曲场和残差连接可改善新型视图合成的性能。我们的代码和数据可在以下网址获得:https://github.com/facebookresearch/multiface
translated by 谷歌翻译