Timezone: »

HyperTime: Implicit Neural Representations for Time Series
Elizabeth Fons · Alejandro Sztrajman · Yousef El-Laham · Alexandros Iosifidis · Svitlana Vyetrenko

Fri Dec 02 09:08 AM -- 09:10 AM (PST) @
Event URL: https://openreview.net/forum?id=DZ2FaoMhWRb »

Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. Their robustness as general approximators has been shown in a wide variety of data sources, with applications on image, sound, and 3D scene representation. However, little attention has been given to leveraging these architectures for the representation and analysis of time series data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. Secondly, we propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset. We introduce an FFT-based loss to guide training so that all frequencies are preserved in the time series.We show that this network can be used to encode time series as INRs, and their embeddings can be interpolated to generate new time series from existing ones. We evaluate our generative method by using it for data augmentation, and show that it is competitive against current state-of-the-art approaches for augmentation of time series.

Author Information

Elizabeth Fons (J.P. Morgan Chase)
Alejandro Sztrajman (University College London)
Yousef El-Laham (J.P. Morgan Chase)
Alexandros Iosifidis (Aarhus University)
Svitlana Vyetrenko (J. P. Morgan, Artificial Intelligence Research)

More from the Same Authors