Explaining Time Series via Contrastive and Locally Sparse Perturbations

Zichuan Liu, Yingying ZHANG, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: time series, explainability, perturbation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A novel perturbation-based method for time series explanation

Abstract:

Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns.
Although previous saliency-based methods addressed the challenges,
their perturbation may not alleviate the distribution shift issue, which is inevitable especially in heterogeneous samples.
We present ContraLSP, a locally sparse model that introduces counterfactual samples to build uninformative perturbations but keeps distribution using contrastive learning.
Furthermore, we incorporate sample-specific sparse gates to generate more binary-skewed and smooth masks, which easily integrate temporal trends and select the salient features parsimoniously.
Empirical studies on both synthetic and real-world datasets show that ContraLSP outperforms state-of-the-art models, demonstrating a substantial improvement in explanation quality for time series data.
The source code is available at \url{https://github.com/zichuan-liu/ContraLSP}.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: visualization or interpretation of learned representations

Submission Number: 6953