Implet: A Post-hoc Subsequence Explainer for Time Series Models

--Explainability in time series models is crucial for fostering trust, facilitating debugging, and ensuring interpretabil-ity in real-world applications. In this work, we introduce Im-plet, a novel post-hoc explainer that generates accurate and concise subsequence-level explanations for time series models. Our approach identifies critical temporal segments that significantly contribute to the model's predictions, providing enhanced interpretability beyond traditional feature-attribution methods. Based on it, we propose a cohort-based (group-level) explanation framework designed to further improve the conciseness and interpretability of our explanations. We evaluate Implet on several standard time-series classification benchmarks, demonstrating its effectiveness in improving interpretability. Deep learning models have demonstrated remarkable success in various time series forecasting and classification tasks, often surpassing traditional statistical methods. Despite their effectiveness, these models are frequently considered black-boxes, making their predictions challenging to interpret. Understanding which temporal patterns or subsequences contribute significantly to a model's decisions is crucial for building trust, debugging erroneous predictions, and making informed decisions, especially in high-stakes domains such as finance, healthcare, and climate science. Existing explainability methods for time series predominantly rely on feature attribution techniques, such as gradient-based saliency maps or perturbation-based approaches. While these methods provide valuable insights into individual time points or features influencing model predictions, their high dimensionality can complicate interpretation. In comparison, subsequence-based explanations, such as shapelet-based methods, are a type of global explanation that offer more intuitive insights by identifying discriminative temporal patterns within time series data.