Can I read Handling Variable-Dimensional Time Series with Graph Neural Networks on EtoBox?

Handling Variable-Dimensional Time Series with Graph Neural Networks by Gupta, Vibhor; Narwariya, Jyoti; Malhotra, Pankaj; Vig, Lovekesh; Shroff, Gautam is a scholarly article available to read on EtoBox.

What is Handling Variable-Dimensional Time Series with Graph Neural Networks about?

Several applications of Internet of Things (IoT) technology involve capturing data from multiple sensors resulting in multi-sensor time series. Existing neural networks based approaches for such multi-sensor or multivariate time series modeling assume fixed input dimension or number of sensors. Such approaches can struggle in the practical setting where different instances of the same device or equipment such as mobiles, wearables, engines, etc. come with different combinations of installed sensors. We consider training neural network models from such multi-sensor time series, where the time series have varying input dimensionality owing to availability or installation of a different subset of sensors at each source of time series. We propose a novel neural network architecture suitable for zero-shot transfer learning allowing robust inference for multivariate time series with previously unseen combination of available dimensions or sensors at test time. Such a combinatorial generalization is achieved by conditioning the layers of a core neural network-based time series model with a "conditioning vector" that carries information of the available combination of sensors for each time

Author

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

Published

2020

Language

EN