HyperTime: Implicit Neural Representation for Time Series
This work addresses the under-explored application of INRs to time series, offering a novel approach for data augmentation and representation, though it is incremental in extending existing INR techniques to a new domain.
The paper tackles the problem of representing and analyzing time series data using implicit neural representations (INRs), showing that a hypernetwork architecture with an FFT-based loss can encode time series for tasks like imputation and data augmentation, achieving competitive results against state-of-the-art methods.
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. We show how these networks can be leveraged for the imputation of time series, with applications on both univariate and multivariate data. Finally, 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.