MoDEx: Mixture of Depth-specific Experts for Multivariate Long-term Time Series Forecasting

• URL: http://arxiv.org/abs/2602.00624v1
• Date: Sat, 31 Jan 2026 09:37:03 GMT
• Title: MoDEx: Mixture of Depth-specific Experts for Multivariate Long-term Time Series Forecasting
• Authors: Hyekyung Yoon, Minhyuk Lee, Imseung Park, Myungjoo Kang,
• Abstract summary: We introduce layer sensitivity, a gradient-based metric inspired by GradCAM and effective receptive field theory.<n>Applying this metric to a three-layer backbone reveals depth-specific expertise in modeling temporal dynamics.<n>MoDEx achieves accuracy on seven real-world benchmarks, ranking first in 78 percent of cases.
• Score: 13.403948071904628
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multivariate long-term time series forecasting (LTSF) supports critical applications such as traffic-flow management, solar-power scheduling, and electricity-transformer monitoring. The existing LTSF paradigms follow a three-stage pipeline of embedding, backbone refinement, and long-horizon prediction. However, the behaviors of individual backbone layers remain underexplored. We introduce layer sensitivity, a gradient-based metric inspired by GradCAM and effective receptive field theory, which quantifies both positive and negative contributions of each time point to a layer's latent features. Applying this metric to a three-layer MLP backbone reveals depth-specific specialization in modeling temporal dynamics in the input sequence. Motivated by these insights, we propose MoDEx, a lightweight Mixture of Depth-specific Experts, which replaces complex backbones with depth-specific MLP experts. MoDEx achieves state-of-the-art accuracy on seven real-world benchmarks, ranking first in 78 percent of cases, while using significantly fewer parameters and computational resources. It also integrates seamlessly into transformer variants, consistently boosting their performance and demonstrating robust generalizability as an efficient and high-performance LTSF framework.

Related papers

• GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder [54.64137490632567]
  We propose a novel and unified framework designed to capture users' sequences from long-term history.<n>Generative Multi-streamers ( GEMs) break user sequences into three streams.<n>Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-the-art methods in recommendation accuracy.
  arXiv  Detail & Related papers  (2026-02-14T06:42:56Z)
• MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts [0.8292000624465587]
  Real-world time series can exhibit intricate multi-scale structures, including global trends, local periodicities, and non-stationary regimes.<n>MoHETS integrates sparse Mixture-of-Heterogeneous-Experts layers.<n>We replace parameter-heavy linear projection heads with a lightweight convolutional patch decoder.
  arXiv  Detail & Related papers  (2026-01-29T15:35:26Z)
• MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping [52.02659589971978]
  We propose MoDES, the first training-free framework that adaptively skips experts to enable efficient and accurate MoE MLLM inference.<n>MoDES significantly enhances inference speed, improving the prefilling time by 2.16$times$ and the decoding time by 1.26$times$.
  arXiv  Detail & Related papers  (2025-11-19T18:48:27Z)
• MGTS-Net: Exploring Graph-Enhanced Multimodal Fusion for Augmented Time Series Forecasting [1.7077661158850292]
  We propose MGTS-Net, a Multimodal Graph-enhanced Network for Time Series forecasting.<n>The model consists of three core components: (1) a Multimodal Feature Extraction layer (MFE), (2) a Multimodal Feature Fusion layer (MFF), and (3) a Multi-Scale Prediction layer (MSP)
  arXiv  Detail & Related papers  (2025-10-18T04:47:10Z)
• DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting [24.202509006348862]
  Time Series Forecasting (TSF) faces persistent challenges in modeling intricate temporal dependencies across different scales.<n>We propose a novel Dynamic Multi-Scale Coordination Framework (DMSC) with Multi-Scale Patch Decomposition block (EMPD), Triad Interaction Block (TIB) and Adaptive Scale Routing MoE block (ASR-MoE)<n>EMPD is designed as a built-in component to dynamically segment sequences into hierarchical patches with exponentially scaled granularities.<n>TIB then jointly models intra-patch, inter-patch, and cross-variable dependencies within each layer's decomposed representations.
  arXiv  Detail & Related papers  (2025-08-03T13:11:52Z)
• A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting [6.344911113059126]
  Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction.<n>This work confronts key issues in LTSF, including the suboptimal use of multi-granularity information.<n>Our method adeptly disentangles complex temporal dynamics using clear, concurrent predictions across various scales.
  arXiv  Detail & Related papers  (2025-05-13T03:26:44Z)
• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction [53.637837706712794]
  Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. We introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction against varying observation periods.
  arXiv  Detail & Related papers  (2024-03-31T17:18:57Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting [46.63798583414426]
  Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis. Our study demonstrates, through both analytical and empirical evidence, that decomposition is key to containing excessive model inflation. Remarkably, by tailoring decomposition to the intrinsic dynamics of time series data, our proposed model outperforms existing benchmarks.
  arXiv  Detail & Related papers  (2024-01-22T13:15:40Z)
• HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting [17.70984737213973]
  HiMTM is a hierarchical multi-scale masked time series modeling with self-distillation for long-term forecasting. HiMTM integrates four key components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales; (2) decoupled encoder-decoder (DED) that directs the encoder towards feature extraction while the decoder focuses on pretext tasks. Experiments on seven mainstream datasets show that HiMTM surpasses state-of-the-art self-supervised and end-to-end learning methods by a considerable margin of 3.16-68.54%.
  arXiv  Detail & Related papers  (2024-01-10T09:00:03Z)
• On the Long Range Abilities of Transformers [69.3021852589771]
  We demonstrate that minimal modifications to the transformer architecture can significantly enhance performance on the Long Range Arena benchmark. We identify that two key principles for long-range tasks are (i.e. incorporating an inductive bias towards smoothness, and (ii.e.) locality. As we show, integrating these ideas into the attention mechanism improves results with a negligible amount of additional computation and without any additional trainable parameters.
  arXiv  Detail & Related papers  (2023-11-28T09:21:48Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)

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.