Imagen de Portada

SPAT: Sensitivity-based Multihead-attention Pruning on Time Series Forecasting Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Suhan, Deng, Jiahong, Yi, Mengjun, Shen, Furao, Zhao, Jian
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting
por: Guo, Suhan, et al.
Publicado: (2024)

Multi-Scale Dilated Convolution Network for Long-Term Time Series Forecasting
por: Li, Feifei, et al.
Publicado: (2024)

T-LLM: Teaching Large Language Models to Forecast Time Series via Temporal Distillation
por: Guo, Suhan, et al.
Publicado: (2026)

Enhancing Epidemic Forecasting: Evaluating the Role of Mobility Data and Graph Convolutional Networks
por: Guo, Suhan, et al.
Publicado: (2025)

MiCA: A Mobility-Informed Causal Adapter for Lightweight Epidemic Forecasting
por: Guo, Suhan, et al.
Publicado: (2026)

Explaining Model Overfitting in CNNs via GMM Clustering
por: Dou, Hui, et al.
Publicado: (2024)

Nested Spatio-Temporal Time Series Forecasting
por: Ai, Yinghao, et al.
Publicado: (2026)

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
por: Zhao, Lifan, et al.
Publicado: (2025)

Dual Prototypes for Adaptive Pre-Trained Model in Class-Incremental Learning
por: Xu, Zhiming, et al.
Publicado: (2024)

Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filtering
por: Dayag, Elisha, et al.
Publicado: (2025)

Region Seeding via Pre-Activation Regularization: A Geometric View of Piecewise Affine Neural Networks
por: Wei, Yi, et al.
Publicado: (2026)

Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting
por: Ou, Wenjie, et al.
Publicado: (2025)

FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecasting
por: Ma, Shusen, et al.
Publicado: (2024)

A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting
por: Kiefer, Nicholas, et al.
Publicado: (2024)

ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
por: Mu, Xinyu, et al.
Publicado: (2025)

AffineLens: Capturing the Continuous Piecewise Affine Functions of Neural Networks
por: Wei, Yi, et al.
Publicado: (2026)

Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
por: Xu, Zhiming, et al.
Publicado: (2025)

Towards Realistic Class-Incremental Learning with Free-Flow Increments
por: Xu, Zhiming, et al.
Publicado: (2026)

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
por: Yang, Suorong, et al.
Publicado: (2025)

Physics-inspired Energy Transition Neural Network for Sequence Learning
por: Wu, Zhou, et al.
Publicado: (2025)

CC-Time: Cross-Model and Cross-Modality Time Series Forecasting
por: Chen, Peng, et al.
Publicado: (2025)

WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting
por: Ou, Wenjie, et al.
Publicado: (2023)

Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
por: Qi, Xuan, et al.
Publicado: (2026)

SEMPO: Lightweight Foundation Models for Time Series Forecasting
por: He, Hui, et al.
Publicado: (2025)

SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasters
por: Shen, ChengAo, et al.
Publicado: (2025)

DBLoss: Decomposition-based Loss Function for Time Series Forecasting
por: Qiu, Xiangfei, et al.
Publicado: (2025)

DAM: Towards A Foundation Model for Time Series Forecasting
por: Darlow, Luke, et al.
Publicado: (2024)

VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
por: Zhang, Xudong, et al.
Publicado: (2026)

Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting
por: Zhao, Lifan, et al.
Publicado: (2024)

Perceiver-based CDF Modeling for Time Series Forecasting
por: Le, Cat P., et al.
Publicado: (2023)

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
por: Zhao, Lifan, et al.
Publicado: (2024)

Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
por: Yang, Yanfeng, et al.
Publicado: (2025)

PA-RNet: Perturbation-Aware Residual Network for Robust Multimodal Time Series Forecasting
por: Zhu, Enqiang, et al.
Publicado: (2025)

Towards Principled Test-Time Adaptation for Time Series Forecasting
por: Wang, Haochun, et al.
Publicado: (2026)

Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis
por: Zhao, Yikai, et al.
Publicado: (2025)

Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting
por: Cheng, Yunyao, et al.
Publicado: (2022)

Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting
por: Yin, Tianyi, et al.
Publicado: (2024)

Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting
por: Cheng, Mingyue, et al.
Publicado: (2026)

CacheFL: Privacy-Preserving and Efficient Federated Cache Model Fine-Tuning for Vision-Language Models
por: Yi, Mengjun, et al.
Publicado: (2025)

HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
por: Feng, Shibo, et al.
Publicado: (2025)