arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.06852cs.LG
收藏

具有可变输入维的多变量时间序列任务的持续学习

Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions

TCS Research(塔塔咨询服务公司研究院)

Vibhor Gupta, Jyoti Narwariya, Pankaj Malhotra, Lovekesh Vig, Gautam Shroff

摘要:

我们考虑一系列相关的多变量时间序列学习任务,例如从多传感器数据的时间序列中预测机器的不同实例的故障,或者从多个可穿戴传感器中对不同个体的活动识别任务。我们专注于在这种环境中出现的两个未充分探索的实际挑战:(i)每个任务可能具有不同的传感器子集,即,提供对基础“系统”的不同部分观察。这种限制可能是由于不同的制造商在前一种情况下,和人们穿着或多或少的测量设备在后者(ii)我们不允许存储或重新访问数据从一个任务,一旦它已被观察到在任务级别。这可能是出于对人的隐私考虑,或者是机器所有者的法律限制。尽管如此,我们希望(a)利用完成任务的经验提高后续任务的性能,以及(b)继续在过去的任务中表现得更好,例如,在从随后观察到的机器中学习之后,更新模型并改进甚至第一台机器上的预测。我们注意到,现有的持续学习方法不考虑由于跨任务可用的传感器的不同子集而产生的输入维度的可变性,并且难以适应这种可变输入维度(VID)任务。在这项工作中,我们解决了现有方法的这一缺点。为此,我们学习特定于任务的生成模型和分类器,并使用它们来增强目标任务的数据。由于任务之间的输入维度不同,我们提出了一种新的条件模块的基础上图神经网络,以帮助一个标准的递归神经网络。我们评估了所提出的方法在三个公开可用的数据集上的有效性,这些数据集对应于两个活动识别任务(分类)和一个统计任务(回归)。

英文摘要:

We consider a sequence of related multivariate time series learning tasks, such as predicting failures for different instances of a machine from time series of multi-sensor data, or activity recognition tasks over different individuals from multiple wearable sensors. We focus on two under-explored practical challenges arising in such settings: (i) Each task may have a different subset of sensors, i.e., providing different partial observations of the underlying 'system'. This restriction can be due to different manufacturers in the former case, and people wearing more or less measurement devices in the latter (ii) We are not allowed to store or re-access data from a task once it has been observed at the task level. This may be due to privacy considerations in the case of people, or legal restrictions placed by machine owners. Nevertheless, we would like to (a) improve performance on subsequent tasks using experience from completed tasks as well as (b) continue to perform better on past tasks, e.g., update the model and improve predictions on even the first machine after learning from subsequently observed ones. We note that existing continual learning methods do not take into account variability in input dimensions arising due to different subsets of sensors being available across tasks, and struggle to adapt to such variable input dimensions (VID) tasks. In this work, we address this shortcoming of existing methods. To this end, we learn task-specific generative models and classifiers, and use these to augment data for target tasks. Since the input dimensions across tasks vary, we propose a novel conditioning module based on graph neural networks to aid a standard recurrent neural network. We evaluate the efficacy of the proposed approach on three publicly available datasets corresponding to two activity recognition tasks (classification) and one prognostics task (regression).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑