File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

이슬기

Lee, Seulki
Embedded Artificial Intelligence Lab.
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

CAFO: Feature-Centric Explanation on Time Series Classification

Author(s)
Kim, JaehoHahn, Seok-JuHwang, YoontaeLee, JunghyeLee, Seulki
Issued Date
2024-08-28
DOI
10.1145/3637528.3671724
URI
https://scholarworks.unist.ac.kr/handle/201301/83846
Fulltext
https://dl.acm.org/doi/10.1145/3637528.3671724
Citation
International Conference on Knowledge Discovery and Data Mining, pp.1372 - 1382
Abstract
In multivariate time series (MTS) classification, finding the important features (e.g., sensors) for model performance is crucial yet challenging due to the complex, high-dimensional nature of MTS data, intricate temporal dynamics, and the necessity for domain-specific interpretations. Current explanation methods for MTS mostly focus on time-centric explanations, apt for pinpointing important time periods but less effective in identifying key features. This limitation underscores the pressing need for a feature-centric approach, a vital yet often overlooked perspective that complements timecentric analysis. To bridge this gap, our study introduces a novel feature-centric explanation and evaluation framework for MTS, named CAFO (Channel Attention and Feature Orthgonalization). CAFO employs a convolution-based approach with channel attention mechanisms, incorporating a depth-wise separable channel attention module (DepCA) and a QR decomposition-based loss for promoting feature-wise orthogonality. We demonstrate that this orthogonalization enhances the separability of attention distributions, thereby refining and stabilizing the ranking of feature importance. This improvement in feature-wise ranking enhances our understanding of feature explainability in MTS. Furthermore, we develop metrics to evaluate global and class-specific feature importance. Our framework’s efficacy is validated through extensive empirical analyses on two major public benchmarks and real-world datasets, both synthetic and self-collected, specifically designed to highlight class-wise discriminative features. The results confirm CAFO’s robustness and informative capacity in assessing feature importance in MTS classification tasks. This study not only advances the understanding of feature-centric explanations in MTS but also sets a foundation for future explorations in feature-centric explanations. The codes are available at https://github.com/eai-lab/CAFO.
Publisher
Association for Computing Machinery

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.