Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

TL;DR

TimeX is a novel self-supervised approach for interpreting time series models by training an interpretable surrogate that maintains model behavior consistency, enabling faithful explanations and pattern recognition.

Contribution

The paper introduces TimeX, a new self-supervised model that improves time series interpretability by preserving relations in the latent space and providing versatile explanation representations.

Findings

TimeX outperforms state-of-the-art methods on multiple datasets.

It provides faithful, interpretable explanations for time series models.

Case studies demonstrate its effectiveness in physiological data analysis.

Abstract

Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to an interpretable temporal pattern. While explainers from other modalities can be applied to time series, their inductive biases do not transfer well to the inherently challenging interpretation of time series. We present TimeX, a time series consistency model for training explainers. TimeX trains an interpretable surrogate to mimic the behavior of a pretrained time series model. It addresses the issue of model faithfulness by introducing model behavior consistency, a novel formulation that preserves relations in the latent space induced by the pretrained model with relations in the latent space induced by TimeX. TimeX provides discrete attribution maps and, unlike existing interpretability methods, it learns a latent space of explanations that can be used in various ways, such as to provide landmarks to visually aggregate similar explanations and easily recognize temporal patterns. We evaluate TimeX on eight synthetic and real-world datasets and compare its performance against state-of-the-art interpretability methods. We also conduct case studies using physiological time series. Quantitative evaluations demonstrate that TimeX achieves the highest or second-highest performance in every metric compared to baselines across all datasets. Through case studies, we show that the novel components of TimeX show potential for training faithful, interpretable models that capture the behavior of pretrained time series models.