Contrastive Learning for Time Series on Dynamic Graphs

TL;DR

This paper introduces GraphTNC, a contrastive learning framework for unsupervised joint representation of multivariate time-series data on dynamic graphs, improving tasks like classification and anomaly detection.

Contribution

It proposes a novel contrastive learning approach that captures the joint dynamics of time-series and graph evolution in an unsupervised manner.

Findings

Effective on synthetic data

Improves classification accuracy on real-world datasets

Utilizes local stationarity assumptions

Abstract

There have been several recent efforts towards developing representations for multivariate time-series in an unsupervised learning framework. Such representations can prove beneficial in tasks such as activity recognition, health monitoring, and anomaly detection. In this paper, we consider a setting where we observe time-series at each node in a dynamic graph. We propose a framework called GraphTNC for unsupervised learning of joint representations of the graph and the time-series. Our approach employs a contrastive learning strategy. Based on an assumption that the time-series and graph evolution dynamics are piecewise smooth, we identify local windows of time where the signals exhibit approximate stationarity. We then train an encoding that allows the distribution of signals within a neighborhood to be distinguished from the distribution of non-neighboring signals. We first demonstrate the performance of our proposed framework using synthetic data, and subsequently we show that it can prove beneficial for the classification task with real-world datasets.