MCNS: Mining Causal Natural Structures Inside Time Series via A Novel Internal Causality Scheme

TL;DR

This paper introduces MCNS, a framework for discovering internal causal structures within time series data, enhancing neural network interpretability and accuracy in classification tasks.

Contribution

The paper proposes a novel, domain-agnostic internal causality scheme and framework (MCNS) for uncovering causal natural structures inside time series, improving neural network performance.

Findings

MCNS improves classification accuracy and interpretability.

Impregnated neural networks with MCNS outperform baseline models.

MCNS provides detailed summaries of time series and datasets.

Abstract

Causal inference permits us to discover covert relationships of various variables in time series. However, in most existing works, the variables mentioned above are the dimensions. The causality between dimensions could be cursory, which hinders the comprehension of the internal relationship and the benefit of the causal graph to the neural networks (NNs). In this paper, we find that causality exists not only outside but also inside the time series because it reflects a succession of events in the real world. It inspires us to seek the relationship between internal subsequences. However, the challenges are the hardship of discovering causality from subsequences and utilizing the causal natural structures to improve NNs. To address these challenges, we propose a novel framework called Mining Causal Natural Structure (MCNS), which is automatic and domain-agnostic and helps to find the causal natural structures inside time series via the internal causality scheme. We evaluate the MCNS framework and impregnation NN with MCNS on time series classification tasks. Experimental results illustrate that our impregnation, by refining attention, shape selection classification, and pruning datasets, drives NN, even the data itself preferable accuracy and interpretability. Besides, MCNS provides an in-depth, solid summary of the time series and datasets.