A0419
Title: Time-aware knowledge representations of dynamic objects with multidimensional persistence
Authors: Yuzhou Chen - University of California, Riverside (United States) [presenting]
Abstract: Learning time-evolving objects such as multivariate time series and dynamic networks requires the development of novel knowledge representation mechanisms and neural network architectures, which allow for capturing implicit time-dependent information contained in the data. Such information is typically not directly observed but plays a key role in the learning task performance. A new approach to a time-aware knowledge representation mechanism is proposed that notably focuses on implicit time-dependent topological information along multiple geometric dimensions. In particular, a new approach is proposed, named temporal multi-persistence (TMP), which produces multidimensional topological fingerprints of the data by using the existing single parameter topological summaries. The main idea behind TMP is to merge the two newest directions in topological representation learning, that is, multi-persistence, which simultaneously describes data shape evolution along multiple key parameters, and zigzag persistence to enable extracting the most salient data shape information over time. Theoretical guarantees of TMP vectorizations are derived, and its utility is shown in its application to forecasting on Ethereum blockchain datasets, demonstrating competitive performance, especially in scenarios of limited data records.
