paper-with-me

Papers

Attention Mamba: Time Series Modeling with Adaptive Pooling Acceleration and Receptive Field Enhancements

2025-04-02 · Sijie Xiong, Shuqing Liu, Cheng Tang, Fumiya Okubo, Haoling Xiong, Atsushi Shimada

"This work has been submitted to the lEEE for possible publication. Copyright may be transferred without noticeafter which this version may no longer be accessible." Time series modeling serves as the cornerstone of real-world applications, such as weather forecasting and transportation management. Recently, Mamba has become a promising model that combines near-linear computational complexity with high prediction accuracy in time series modeling, while facing challenges such as insufficient modeling of nonlinear dependencies in attention and restricted receptive fields caused by convolutions. To overcome these limitations, this paper introduces an innovative framework, Attention Mamba, featuring a novel Adaptive Pooling block that accelerates attention computation and incorporates global information, effectively overcoming the constraints of limited receptive fields. Furthermore, Attention Mamba integrates a bidirectional Mamba block, efficiently capturing long-short features and transforming inputs into the Value representations for attention mechanisms. Extensive experiments conducted on diverse datasets underscore the effectiveness of Attention Mamba in extracting nonlinear dependencies and enhancing receptive fields, establishing superior performance among leading counterparts. Our codes will be available on GitHub.

📄 PDF Abstract BibTeX arXiv:2504.02013

Code (0)

등록된 구현이 없습니다.

Tasks

MambaTime SeriesWeather Forecasting

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

Mamba or Transformer for Time Series Forecasting? Mixture of Universals (MoU) Is All You Need

2024-08-28 · Sijia Peng, Yun Xiong, Yangyong Zhu, Zhiqiang Shen

Time series forecasting requires balancing short-term and long-term dependencies for accurate predictions. Existing methods mainly focus on long-term dependency modeling, neglecting the complexities of short-term dynamic…

AllMambaTime SeriesTime Series Forecasting

MAAT: Mamba Adaptive Anomaly Transformer with association discrepancy for time series

2025-02-11 · Abdellah Zakaria Sellam, Ilyes Benaissa, Abdelmalik Taleb-Ahmed, Luigi Patrono 외

Anomaly detection in time series is essential for industrial monitoring and environmental sensing, yet distinguishing anomalies from complex patterns remains challenging. Existing methods like the Anomaly Transformer and…

Anomaly DetectionAnomaly LocalizationMambaTime Series+1

AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting

2026-04-25 · Xudong Jiang, Mingshan Loo, Hanchen Yang, Wengen Li 외 arxiv

Accurate long-term time series forecasting (LTSF) requires the capture of complex long-range dependencies and dynamic periodic patterns. Recent advances in frequency-domain analysis offer a global perspective for uncover…

Computational EfficiencyTime Series Forecasting

UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration

2026-03-06 · Xingsheng Chen, Xianpei Mu, Deyu Yi, Yilin Yuan 외 arxiv

Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges.…

Multivariate Time Series ForecastingComputational Efficiency

DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis

2026-01-09 · Rui An, Haohao Qu, Wenqi Fan, Xuequn Shang 외 arxiv

Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to th…

Computational EfficiencyTime Series AnalysisAnomaly Detection