Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

Abstract

There recently has been a surge of interest in developing a new class of deep learning (DL) architectures that integrate an explicit time dimension as a fundamental building block of learning and representation mechanisms. In turn, many recent results show that topological descriptors of the observed data, encoding information on the shape of the dataset in a topological space at different scales, that is, persistent homology of the data, may contain important complementary information, improving both performance and robustness of DL. As convergence of these two emerging ideas, we propose to enhance DL architectures with the most salient time-conditioned topological information of the data and introduce the concept of zigzag persistence into time-aware graph convolutional networks (GCNs). Zigzag persistence provides a systematic and mathematically rigorous framework to track the most important topological features of the observed data that tend to manifest themselves over time. To integrate the extracted time-conditioned topological descriptors into DL, we develop a new topological summary, zigzag persistence image, and derive its theoretical stability guarantees. We validate the new GCNs with a time-aware zigzag topological layer (Z-GCNETs), in application to traffic forecasting and Ethereum blockchain price prediction. Our results indicate that Z-GCNET outperforms 13 state-of-the-art methods on 4 time series datasets.

arXiv commentAccepted at the International Conference on Machine Learning (ICML) 2021

References in corpus (11)

• Sequence to Sequence Learning with Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• LSTM: A Search Space Odyssey
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Evasion Paths in Mobile Sensor Networks
• Applications of Zigzag Persistence to Topological Data Analysis
• The Importance of Forgetting: Limiting Memory Improves Recovery of Topological Characteristics from Neural Data
• Capturing Dynamics of Time-Varying Data via Topology
• A torus model for optical flow

Cited by in corpus (2)

• Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders