Global Explanations for Multivariate Time Series Forecasting Models via $K$-Order Markov Approximations

• URL: http://arxiv.org/abs/2606.27599v1
• Date: Thu, 25 Jun 2026 23:09:03 GMT
• Title: Global Explanations for Multivariate Time Series Forecasting Models via $K$-Order Markov Approximations
• Abstract summary: We introduce BeijingtextscKARMA, a method for explaining time-series predictors by constructing a Markov surrogate model.<n>Our approach revolves around three main aspects: identifying the minimal history length $K$ that is predictively sufficient for the model.<n>We also certify using complex synthetic data with known true causal edges that KARMA recovers the data causal structure as learned by the model via a controlled experiment.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While many explainable AI (XAI) methods have been proposed, most are not designed for time-series forecasting models and often rely on the implicit assumption that timestamp features are independent. This assumption ignores the fundamental property of temporal dependence and can lead to explanations that violate the sequential and causal structure of the data. We introduce \textsc{KARMA}, a method for explaining time-series predictors by constructing a Markov surrogate model that captures the temporal dependencies learned by the predictor. Our approach revolves around three main aspects: identifying the minimal history length $K$ that is predictively sufficient for the model, estimating the best-fitting $K$-order Markov transition kernel from the discretized history space, and a five-level global explanation hierarchy that can be derived from the Markov transition kernel, which we illustrate using real-world weather data (Beijing PM 2.5). We also certify using complex synthetic data with known true causal edges that KARMA (i) recovers the data causal structure as learned by the model via a controlled experiment and (ii) identifies temporal dependencies better than established attribution methods such as TimeSHAP.

Related papers

• ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting [54.57031153712623]
  ARIES is a framework for assessing relation between time series properties and modeling strategies.<n>We propose the first deep forecasting model recommender, capable of providing interpretable suggestions for real-world time series.
  arXiv  Detail & Related papers  (2025-09-07T13:57:14Z)
• Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift [51.01356105618118]
  Time series often exhibit complex non-uniform distribution with varying patterns across segments, such as season, operating condition, or semantic meaning.<n>Existing approaches, which typically train a single model to capture all these diverse patterns, often struggle with the pattern drifts between patches.<n>We propose TFPS, a novel architecture that leverages pattern-specific experts for more accurate and adaptable time series forecasting.
  arXiv  Detail & Related papers  (2024-10-13T13:35:29Z)
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs [50.25683648762602]
  We introduce Koopman VAE, a new generative framework that is based on a novel design for the model prior. Inspired by Koopman theory, we represent the latent conditional prior dynamics using a linear map. KoVAE outperforms state-of-the-art GAN and VAE methods across several challenging synthetic and real-world time series generation benchmarks.
  arXiv  Detail & Related papers  (2023-10-04T07:14:43Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• Information Theory Inspired Pattern Analysis for Time-series Data [60.86880787242563]
  We propose a highly generalizable method that uses information theory-based features to identify and learn from patterns in time-series data. For applications with state transitions, features are developed based on Shannon's entropy of Markov chains, entropy rates of Markov chains, and von Neumann entropy of Markov chains. The results show the proposed information theory-based features improve the recall rate, F1 score, and accuracy on average by up to 23.01% compared with the baseline models.
  arXiv  Detail & Related papers  (2023-02-22T21:09:35Z)
• An Interpretable and Efficient Infinite-Order Vector Autoregressive Model for High-Dimensional Time Series [1.4939176102916187]
  This paper proposes a novel sparse infinite-order VAR model for high-dimensional time series. The temporal and cross-sectional structures of the VARMA-type dynamics captured by this model can be interpreted separately. Greater statistical efficiency and interpretability can be achieved with little loss of temporal information.
  arXiv  Detail & Related papers  (2022-09-02T17:14:24Z)
• Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report [70.7321040534471]
  Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. There is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting.
  arXiv  Detail & Related papers  (2021-09-01T09:52:31Z)
• Partially Hidden Markov Chain Linear Autoregressive model: inference and forecasting [0.0]
  Time series subject to change in regime have attracted much interest in domains such as econometry, finance or meteorology. We present a novel model which addresses the intermediate case: (i) state processes associated to such time series are modelled by Partially Hidden Markov Chains (PHMCs) We propose a hidden state inference procedure and a forecasting function that take into account the observed states when existing.
  arXiv  Detail & Related papers  (2021-02-24T22:12:05Z)
• Feature Importance Explanations for Temporal Black-Box Models [3.655021726150369]
  We propose TIME, a method to explain models that are inherently temporal in nature. Our approach uses a model-agnostic permutation-based approach to analyze global feature importance.
  arXiv  Detail & Related papers  (2021-02-23T20:41:07Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Variational Conditional Dependence Hidden Markov Models for Skeleton-Based Action Recognition [7.9603223299524535]
  This paper revisits conventional sequential modeling approaches, aiming to address the problem of capturing time-varying temporal dependency patterns. We propose a different formulation of HMMs, whereby the dependence on past frames is dynamically inferred from the data. We derive a tractable inference algorithm based on the forward-backward algorithm.
  arXiv  Detail & Related papers  (2020-02-13T23:18:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.