Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (10) , 11678-11686
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. In turn, lack of time dimension in knowledge encoding mechanisms for time-dependent data leads to frequent model updates, poor learning performance, and, as a result, subpar decision-making. Here we propose a new approach to a time-aware knowledge representation mechanism that notably focuses on implicit time-dependent topological information along multiple geometric dimensions. In particular, we propose a new approach, named Temporal MultiPersistence (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 us to extract the most salient data shape information over time. We derive theoretical guarantees of TMP vectorizations and show its utility, in application to forecasting on benchmark traffic flow, Ethereum blockchain, and electrocardiogram datasets, demonstrating the competitive performance, especially, in scenarios of limited data records. In addition, our TMP method improves the computational efficiency of the state-of-the-art multipersistence summaries up to 59.5 times.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Signed Barcodes for Multi-parameter Persistence via Rank Decompositions and Rank-Exact ResolutionsFoundations of Computational Mathematics, 2024
- Graph neural network for traffic forecasting: A surveyExpert Systems with Applications, 2022
- Persistence Curves: A canonical framework for summarizing persistence diagramsAdvances in Computational Mathematics, 2022
- Blockchain networks: Data structures of Bitcoin, Monero, Zcash, Ethereum, Ripple, and IotaWIREs Data Mining and Knowledge Discovery, 2021
- On the stability of persistent entropy and new summary functions for topological data analysisPattern Recognition, 2020
- Tokens, Types, and Standards: Identification and Utilization in Ethereum2020
- Skeleton-Based Dynamic Hand Gesture Recognition Using a Part-Based GRU-RNN for Gesture-Based InterfaceIEEE Access, 2020
- A survey on graph kernelsApplied Network Science, 2020
- A kernel for multi-parameter persistent homologyComputers & Graphics: X, 2019
- Persistence homology of networks: methods and applicationsApplied Network Science, 2019