Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning

TL;DR

SelfTime introduces a novel self-supervised framework for time series representation learning by jointly exploring inter-sample and intra-temporal relations, significantly improving classification performance on real-world datasets.

Contribution

The paper proposes a unified approach that leverages both inter-sample and intra-temporal relations for better time series representations, filling a gap in existing methods.

Findings

Effective on multiple real-world datasets

Outperforms existing self-supervised methods

Improves time series classification accuracy

Abstract

Self-supervised learning achieves superior performance in many domains by extracting useful representations from the unlabeled data. However, most of traditional self-supervised methods mainly focus on exploring the inter-sample structure while less efforts have been concentrated on the underlying intra-temporal structure, which is important for time series data. In this paper, we present SelfTime: a general self-supervised time series representation learning framework, by exploring the inter-sample relation and intra-temporal relation of time series to learn the underlying structure feature on the unlabeled time series. Specifically, we first generate the inter-sample relation by sampling positive and negative samples of a given anchor sample, and intra-temporal relation by sampling time pieces from this anchor. Then, based on the sampled relation, a shared feature extraction backbone combined with two separate relation reasoning heads are employed to quantify the relationships of the sample pairs for inter-sample relation reasoning, and the relationships of the time piece pairs for intra-temporal relation reasoning, respectively. Finally, the useful representations of time series are extracted from the backbone under the supervision of relation reasoning heads. Experimental results on multiple real-world time series datasets for time series classification task demonstrate the effectiveness of the proposed method. Code and data are publicly available at https://haoyfan.github.io/.