Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions

03/14/2022
by   Vibhor Gupta, et al.
4

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).

READ FULL TEXT
research
07/01/2020

Handling Variable-Dimensional Time Series with Graph Neural Networks

Several applications of Internet of Things(IoT) technology involve captu...
research
01/26/2023

Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning

With the rapid development of wearable cameras, a massive collection of ...
research
03/11/2022

Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks

Continual learning, also known as lifelong learning, is an emerging rese...
research
07/06/2020

Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization

Given the growing trend of continual learning techniques for deep neural...
research
01/03/2022

Multivariate Time Series Regression with Graph Neural Networks

Machine learning, with its advances in Deep Learning has shown great pot...
research
04/19/2021

Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis

Sensor-based human activity recognition (HAR), i.e., the ability to disc...
research
05/13/2019

Federated Multi-task Hierarchical Attention Model for Sensor Analytics

Sensors are an integral part of modern Internet of Things (IoT) applicat...

Please sign up or login with your details

Forgot password? Click here to reset