Image de couverture de livre

Class-Dependent Perturbation Effects in Evaluating Time Series Attributions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Baer, Gregor, Grau, Isel, Zhang, Chao, Van Gorp, Pieter
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Why Do Class-Dependent Evaluation Effects Occur with Time Series Feature Attributions? A Synthetic Data Investigation
par: Baer, Gregor, et autres
Publié: (2025)

Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding
par: Baer, Gregor, et autres
Publié: (2026)

xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth
par: Baer, Gregor
Publié: (2026)

Class-incremental Learning for Time Series: Benchmark and Evaluation
par: Qiao, Zhongzheng, et autres
Publié: (2024)

Explaining Time Series via Contrastive and Locally Sparse Perturbations
par: Liu, Zichuan, et autres
Publié: (2024)

An Automated Approach to Collecting and Labeling Time Series Data for Event Detection Using Elastic Node Hardware
par: Ling, Tianheng, et autres
Publié: (2024)

Warping and Matching Subsequences Between Time Series
par: Lin, Simiao, et autres
Publié: (2025)

Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching
par: Zhang, Jintao, et autres
Publié: (2025)

On-device AI: Quantization-aware Training of Transformers in Time-Series
par: Ling, Tianheng, et autres
Publié: (2024)

Explaining Time Series Classification Predictions via Causal Attributions
par: Alcaraz, Juan Miguel Lopez, et autres
Publié: (2024)

SEED: Spectral Entropy-Guided Evaluation of SpatialTemporal Dependencies for Multivariate Time Series Forecasting
par: Xiong, Feng, et autres
Publié: (2025)

FreqLens: Interpretable Frequency Attribution for Time Series Forecasting
par: Chen, Chi-Sheng, et autres
Publié: (2026)

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
par: Liu, Juncheng, et autres
Publié: (2024)

Time-Series Contrastive Learning against False Negatives and Class Imbalance
par: Jin, Xiyuan, et autres
Publié: (2023)

Multivariate Time Series Anomaly Detection by Capturing Coarse-Grained Intra- and Inter-Variate Dependencies
par: Xie, Yongzheng, et autres
Publié: (2025)

Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
par: Kang, Bong Gyun, et autres
Publié: (2024)

Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
par: Mozolewski, Maciej, et autres
Publié: (2025)

Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT
par: Ling, Tianheng, et autres
Publié: (2024)

On-Device Soft Sensors: Real-Time Fluid Flow Estimation from Level Sensor Data
par: Ling, Tianheng, et autres
Publié: (2023)

One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Data
par: Luetto, Simone, et autres
Publié: (2023)

Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models
par: Wang, Zhengguang
Publié: (2024)

Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition
par: Li, Dongyuan, et autres
Publié: (2026)

Leaning Time-Varying Instruments for Identifying Causal Effects in Time-Series Data
par: Cheng, Debo, et autres
Publié: (2024)

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
par: Zhao, Lifan, et autres
Publié: (2024)

Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach
par: Nieradzik, Lars, et autres
Publié: (2024)

Evaluating Simplification Algorithms for Interpretability of Time Series Classification
par: Håvardstun, Brigt, et autres
Publié: (2025)

Training and Evaluating Causal Forecasting Models for Time-Series
par: Crasson, Thomas, et autres
Publié: (2024)

Anomalous Agreement: How to find the Ideal Number of Anomaly Classes in Correlated, Multivariate Time Series Data
par: Rewicki, Ferdinand, et autres
Publié: (2025)

Estimating Time Series Foundation Model Transferability via In-Context Learning
par: Yao, Qingren, et autres
Publié: (2025)

Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
par: B, Thackshanaramana
Publié: (2026)

Long Input Sequence Network for Long Time Series Forecasting
par: Ma, Chao, et autres
Publié: (2024)

CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection
par: Zhong, Zhijie, et autres
Publié: (2025)

STEB: In Search of the Best Evaluation Approach for Synthetic Time Series
par: Stenger, Michael, et autres
Publié: (2025)

Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filtering
par: Dayag, Elisha, et autres
Publié: (2025)

IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Prediction
par: Zhou, Yifan, et autres
Publié: (2025)

Breaking the Context Bottleneck on Long Time Series Forecasting
par: Ma, Chao, et autres
Publié: (2024)

DeCoP: Enhancing Self-Supervised Time Series Representation with Dependency Controlled Pre-training
par: Wu, Yuemin, et autres
Publié: (2025)

MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting
par: Wu, Binqing, et autres
Publié: (2025)

SciTS: Scientific Time Series Understanding and Generation with LLMs
par: Wu, Wen, et autres
Publié: (2025)

Large Language Models are Few-shot Multivariate Time Series Classifiers
par: Chen, Yakun, et autres
Publié: (2025)