Cover Image

PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kreuzer, Tim, Zdravkovic, Jelena, Papapetrou, Panagiotis
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards plausibility in time series counterfactual explanations
by: Kostrzewa, Marcin, et al.
Published: (2026)

CNN-TFT explained by SHAP with multi-head attention weights for time series forecasting
by: Stefenon, Stefano F., et al.
Published: (2025)

Towards a perturbation-based explanation for medical AI as differentiable programs
by: Abe, Takeshi, et al.
Published: (2025)

Grey-informed neural network for time-series forecasting
by: Xie, Wanli, et al.
Published: (2024)

Temporal Fusion Nexus: A task-agnostic multi-modal embedding model for clinical narratives and irregular time series in post-kidney transplant care
by: Kumar, Aditya, et al.
Published: (2026)

Foundation models for time series forecasting: Application in conformal prediction
by: Achour, Sami, et al.
Published: (2025)

Generative Correlation Manifolds: Generating Synthetic Data with Preserved Higher-Order Correlations
by: d'Hondt, Jens E., et al.
Published: (2025)

Less is more: Embracing sparsity and interpolation with Esiformer for time series forecasting
by: Guo, Yangyang, et al.
Published: (2024)

Enhancing few-shot time series forecasting with LLM-guided diffusion
by: Shi, Haonan, et al.
Published: (2026)

DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
by: Morel, Rudy, et al.
Published: (2025)

Interactive dense pixel visualizations for time series and model attribution explanations
by: Schlegel, Udo, et al.
Published: (2024)

A federated large language model for long-term time series forecasting
by: Abdel-Sater, Raed, et al.
Published: (2024)

WEITS: A Wavelet-enhanced residual framework for interpretable time series forecasting
by: Guo, Ziyou, et al.
Published: (2024)

What is the best RNN-cell structure to forecast each time series behavior?
by: Khaldi, Rohaifa, et al.
Published: (2022)

A decoder-only foundation model for time-series forecasting
by: Das, Abhimanyu, et al.
Published: (2023)

Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust
by: Erlygin, Leonid, et al.
Published: (2023)

A multi-criteria approach for selecting an explanation from the set of counterfactuals produced by an ensemble of explainers
by: Stępka, Ignacy, et al.
Published: (2024)

Introducing δ-XAI: a novel sensitivity-based method for local AI explanations
by: De Carlo, Alessandro, et al.
Published: (2024)

Model-agnostic Selective Labeling with Provable Statistical Guarantees
by: Huang, Huipeng, et al.
Published: (2025)

Data re-uploading in Quantum Machine Learning for time series: application to traffic forecasting
by: Schetakis, Nikolaos, et al.
Published: (2025)

Universal time-series forecasting with mixture predictors
by: Ryabko, Daniil
Published: (2020)

Bond Graphs for multi-physics informed Neural Networks for multi-variate time series
by: Brachet, Alexis-Raja, et al.
Published: (2024)

S4M: S4 for multivariate time series forecasting with Missing values
by: Peng, Jing, et al.
Published: (2025)

Context information can be more important than reasoning for time series forecasting with a large language model
by: Yang, Janghoon
Published: (2025)

FlowTS: Time Series Generation via Rectified Flow
by: Hu, Yang, et al.
Published: (2024)

Neuroplasticity-inspired dynamic ANNs for multi-task demand forecasting
by: Żarski, Mateusz, et al.
Published: (2025)

Enabling Regional Explainability by Automatic and Model-agnostic Rule Extraction
by: Chen, Yu, et al.
Published: (2024)

Heterogeneity-agnostic AI/ML-assisted beam selection for multi-panel arrays
by: Kilinc, Ibrahim, et al.
Published: (2026)

Short-term electricity load forecasting with multi-frequency reconstruction diffusion
by: Dong, Qi, et al.
Published: (2026)

Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
by: Xia, Shuyin, et al.
Published: (2023)

MADCluster: Model-agnostic Anomaly Detection with Self-supervised Clustering Network
by: Lee, Sangyong, et al.
Published: (2025)

DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
by: Li, Rongqing, et al.
Published: (2024)

Rad4XCNN: a new agnostic method for post-hoc global explanation of CNN-derived features by means of radiomics
by: Prinzi, Francesco, et al.
Published: (2024)

Decomposition-based multi-scale transformer framework for time series anomaly detection
by: Zhang, Wenxin, et al.
Published: (2025)

ExplainReduce: Generating global explanations from many local explanations
by: Seppäläinen, Lauri, et al.
Published: (2025)

Personalized Federated Continual Learning via Multi-granularity Prompt
by: Yu, Hao, et al.
Published: (2024)

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models
by: Lyu, Sisuo, et al.
Published: (2026)

UniTS: A Unified Multi-Task Time Series Model
by: Gao, Shanghua, et al.
Published: (2024)

Model Science: getting serious about verification, explanation and control of AI systems
by: Biecek, Przemyslaw, et al.
Published: (2025)

A robust three-way classifier with shadowed granular-balls based on justifiable granularity
by: Yang, Jie, et al.
Published: (2024)