EXCODER: EXplainable Classification Of DiscretE time series Representations
This work addresses the problem of interpretability in time series analysis for researchers and practitioners, offering an incremental improvement by combining existing methods with a new validation metric.
The paper tackles the challenge of explainability in deep learning for time series classification by investigating whether transforming time series into discrete latent representations enhances explainability, showing that this approach leads to concise and structured explanations without sacrificing performance and proposing a novel metric, Similar Subsequence Accuracy (SSA), to validate the alignment of XAI-identified features with training data.
Deep learning has significantly improved time series classification, yet the lack of explainability in these models remains a major challenge. While Explainable AI (XAI) techniques aim to make model decisions more transparent, their effectiveness is often hindered by the high dimensionality and noise present in raw time series data. In this work, we investigate whether transforming time series into discrete latent representations-using methods such as Vector Quantized Variational Autoencoders (VQ-VAE) and Discrete Variational Autoencoders (DVAE)-not only preserves but enhances explainability by reducing redundancy and focusing on the most informative patterns. We show that applying XAI methods to these compressed representations leads to concise and structured explanations that maintain faithfulness without sacrificing classification performance. Additionally, we propose Similar Subsequence Accuracy (SSA), a novel metric that quantitatively assesses the alignment between XAI-identified salient subsequences and the label distribution in the training data. SSA provides a systematic way to validate whether the features highlighted by XAI methods are truly representative of the learned classification patterns. Our findings demonstrate that discrete latent representations not only retain the essential characteristics needed for classification but also offer a pathway to more compact, interpretable, and computationally efficient explanations in time series analysis.