1.
the consistency constraint 一致性约束
consistency :n.连贯;符合;前后一致;浓度;
2.
We demonstrate empirically that our method helps preserve channel/feature correlations and that our synthetic data performs very well in downstream tasks with medical and financial data.
我们通过经验证明,我们的方法有助于保持通道/特征相关性,并且我们的合成数据在下游任务中与医疗和金融数据一起表现得非常好。
3.
We demonstrate empirically that our method helps preserve channel/feature correlations and that our synthetic data performs very well in downstream tasks with medical and financial data.
我们通过经验证明,我们的方法有助于保持通道/特征相关性,并且我们的合成数据在下游任务中与医疗和金融数据一起表现得非常好。
有助于保持通道/特征相关性:helps preserve channel/feature correlations
4.
We propose a novel framework that takes time series’ common origin into account and favors channel/feature relationships preservation.
提出了一种新的时间序列分析框架,该框架考虑了时间序列的共同起源,并支持通道/特征关系的保持.
考虑了时间序列的共同起源:takes time series’ common origin into account
支持通道/特征关系的保持:favors channel/feature relationships preservation
5.
There is valuable information in those patterns that machine learning models can use to better classify, predict or perform other downstream tasks.
这些模式中包含有价值的信息,机器学习模型可以使用这些信息更好地进行分类、预测或执行其他下游任务。
这些模式中包含有价值的信息:there is valuable information in those patterns
6.
Generating multivariate time series is a promising approach for sharing sensitive data in many medical, financial, and IoT applications.
生成多元时间序列是一种很有前途的方法,可用于在许多医疗、金融和物联网应用中共享敏感数据。
A common type of multivariate time series originates from a single source such as the biometric measurements from a medical patient.
This leads to complex dynamical patterns between individual time series that are hard to learn by typical generation models such as GANs.
常见类型的多变量时间序列源自单个源,诸如来自医疗患者的生物测定测量。
这导致了个体时间序列之间的复杂动态模式,这很难通过典型的生成模型(如GAN)来学习。
一种很有前途的方法:a promising approach
共享敏感数据:sharing sensitive data
复杂动态模式:complex dynamical patterns
典型的生成模型:typical generation models
7.
Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
非静止变压器:时间序列预测中平稳性的探讨
8.
Transformers have shown great power in time series forecasting due to their global-range modeling ability.
However, their performance can degenerate terribly on non-stationary real-world data in which the joint distribution changes over time.
然而,在联合分布随时间变化的非平稳真实世界数据上,它们的性能可能会严重退化。
shown great power
global-range modeling ability
degenerate terribly: 性能可能会严重退化
non-stationary real-world data in which the joint distribution changes over time
9.
Previous studies primarily adopt stationarization to attenuate the non-stationarity of original series for better predictability.
But the stationarized series deprived of inherent non-stationarity can be less instructive for real-world bursty events forecasting.
以往的研究主要采用平稳化的方法来减弱原始序列的非平稳性,以提高预测能力。
但是,失去了固有非平稳性的平稳序列对实际突发事件的预测指导意义不大。
attenuate the non-stationarity of original series
attenuate: v.(使)减弱;(使)纤细,稀薄
be less instructive: 指导意义不大
10.
bursty events: 突发事件