MIX: A Multi-view Time-Frequency Interactive Explanation Framework for Time Series Classification

Deep learning models for time series classification (TSC) have achieved impressive performance, but explaining their decisions remains a significant challenge. Existing post-hoc explanation methods typically operate solely in the time domain and from a single-view perspective, limiting both faithfulness and robustness. In this work, we propose MIX (Multi-view Time-Frequency Interactive EXplanation Framework), a novel framework that helps to explain deep learning models in a multi-view setting by leveraging multi-resolution, time-frequency views constructed using the Haar Discrete Wavelet Transform (DWT). MIX introduces an interactive cross-view refinement scheme, where explanation's information from one view is propagated across views to enhance overall interpretability. To align with user-preferred perspectives, we propose a greedy selection strategy that traverses the multi-view space to identify the most informative features. Additionally, we present OSIGV, a user-aligned segment-level attribution mechanism based on overlapping windows for each view, and introduce keystone-first IG, a method that refines explanations in each view using additional information from another view. Extensive experiments across multiple TSC benchmarks and model architectures demonstrate that MIX significantly outperforms state-of-the-art (SOTA) methods in terms of explanation faithfulness and robustness.

Authors

• Viet-Hung Tran The Queen's University Belfast
• Ngoc Phu Doan The Queen's University Belfast
• Zichi Zhang The Queen's University Belfast
• Tuan Pham
• Phi Hung Nguyen
• Xuan Nguyen
• Hans Vandierendonck The Queen's University Belfast
• Ira Assent Aarhus University
• Thai Son Mai

Keywords

No keywords are indexed for this paper.