MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEs

• URL: http://arxiv.org/abs/2601.00920v1
• Date: Thu, 01 Jan 2026 11:23:20 GMT
• Title: MODE: Efficient Time Series Prediction with Mamba Enhanced by Low-Rank Neural ODEs
• Authors: Xingsheng Chen, Regina Zhang, Bo Gao, Xingwei He, Xiaofeng Liu, Pietro Lio, Kwok-Yan Lam, Siu-Ming Yiu,
• Abstract summary: Time series prediction plays a pivotal role across diverse domains such as finance, healthcare, energy systems, and environmental modeling.<n>We propose MODE, a unified framework that integrates Low-Rank Neural Ordinary Differential Equations (Neural ODEs) with an Enhanced Mamba architecture.<n>Our contributions include: (1) a unified and efficient architecture for long-term time series modeling, (2) integration of Mamba's selective scanning with low-rank Neural ODEs for enhanced temporal representation, and (3) substantial improvements in efficiency and scalability enabled by low-rank approximation and dynamic selective scanning.
• Score: 41.50535363508025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time series prediction plays a pivotal role across diverse domains such as finance, healthcare, energy systems, and environmental modeling. However, existing approaches often struggle to balance efficiency, scalability, and accuracy, particularly when handling long-range dependencies and irregularly sampled data. To address these challenges, we propose MODE, a unified framework that integrates Low-Rank Neural Ordinary Differential Equations (Neural ODEs) with an Enhanced Mamba architecture. As illustrated in our framework, the input sequence is first transformed by a Linear Tokenization Layer and then processed through multiple Mamba Encoder blocks, each equipped with an Enhanced Mamba Layer that employs Causal Convolution, SiLU activation, and a Low-Rank Neural ODE enhancement to efficiently capture temporal dynamics. This low-rank formulation reduces computational overhead while maintaining expressive power. Furthermore, a segmented selective scanning mechanism, inspired by pseudo-ODE dynamics, adaptively focuses on salient subsequences to improve scalability and long-range sequence modeling. Extensive experiments on benchmark datasets demonstrate that MODE surpasses existing baselines in both predictive accuracy and computational efficiency. Overall, our contributions include: (1) a unified and efficient architecture for long-term time series modeling, (2) integration of Mamba's selective scanning with low-rank Neural ODEs for enhanced temporal representation, and (3) substantial improvements in efficiency and scalability enabled by low-rank approximation and dynamic selective scanning.

Related papers

• TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [59.99922360648663]
  TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
  arXiv  Detail & Related papers  (2025-12-12T11:55:16Z)
• MMA: A Momentum Mamba Architecture for Human Activity Recognition with Inertial Sensors [6.7394387525196215]
  Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence.<n>We introduce Momentum Mamba, a momentum-augmented SSM that incorporates second-order dynamics to improve stability of information flow across time steps.<n> Experiments on multiple HAR benchmarks demonstrate consistent gains over vanilla Mamba and Transformer baselines in accuracy, robustness, and convergence speed.
  arXiv  Detail & Related papers  (2025-11-26T16:21:36Z)
• Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM [4.120576565537633]
  Existing deep learning models for Predictive Process Monitoring (PPM) struggle with temporal irregularities.<n>We propose a dual input neural network strategy that separates event and sequence attributes, using a duration-aware pseudo-embedding matrix.<n>Our results demonstrate the benefits of explicit temporal encoding and provide a flexible design for robust, real-world PPM applications.
  arXiv  Detail & Related papers  (2025-11-24T07:06:08Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements [46.19047880604178]
  We recast time-series problems as the continuous ODE-based optimal control problem.<n>Rather than learning dynamics solely from data, we optimize control actions that steer ODE trajectories toward task objectives.<n>We show that, under mild assumptions, this multi-horizon optimization leads to exponential convergence to infinite-horizon solutions.
  arXiv  Detail & Related papers  (2025-08-03T16:41:00Z)
• Sequential-Parallel Duality in Prefix Scannable Models [68.39855814099997]
  Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba.<n>This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference?
  arXiv  Detail & Related papers  (2025-06-12T17:32:02Z)
• UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba [7.594115034632109]
  We propose UmambaTSF, a novel long-term time series forecasting framework. It integrates multi-scale feature extraction capabilities of U-shaped encoder-decoder multilayer perceptrons (MLP) with Mamba's long sequence representation. UmambaTSF achieves state-of-the-art performance and excellent generality on widely used benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-15T04:56:43Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• Mamba-Spike: Enhancing the Mamba Architecture with a Spiking Front-End for Efficient Temporal Data Processing [4.673285689826945]
  Mamba-Spike is a novel neuromorphic architecture that integrates a spiking front-end with the Mamba backbone to achieve efficient temporal data processing. The architecture consistently outperforms state-of-the-art baselines, achieving higher accuracy, lower latency, and improved energy efficiency.
  arXiv  Detail & Related papers  (2024-08-04T14:10:33Z)
• Gait Recognition in the Wild with Multi-hop Temporal Switch [81.35245014397759]
  gait recognition in the wild is a more practical problem that has attracted the attention of the community of multimedia and computer vision. This paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes.
  arXiv  Detail & Related papers  (2022-09-01T10:46:09Z)

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.