ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecasting

• URL: http://arxiv.org/abs/2601.20611v1
• Date: Wed, 28 Jan 2026 13:47:54 GMT
• Title: ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecasting
• Abstract summary: Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations.<n>We propose ACFormer, an architecture designed to reconcile the efficiency of linear projections with the non-linear feature-extraction power of convolutions.
• Score: 6.27761817493579
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the efficiency of linear architectures in capturing global trends, these models often struggle with non-linear signals. To address this gap, we conducted a systematic receptive field analysis of convolutional neural network (CNN) TSF models. We introduce the "individual receptive field" to uncover granular structural dependencies, revealing that convolutional layers act as feature extractors that mirror channel-wise attention while exhibiting superior robustness to non-linear fluctuations. Based on these insights, we propose ACFormer, an architecture designed to reconcile the efficiency of linear projections with the non-linear feature-extraction power of convolutions. ACFormer captures fine-grained information through a shared compression module, preserves temporal locality via gated attention, and reconstructs variable-specific temporal patterns using an independent patch expansion layer. Extensive experiments on multiple benchmark datasets demonstrate that ACFormer consistently achieves state-of-the-art performance, effectively mitigating the inherent drawbacks of linear models in capturing high-frequency components.

Related papers

• STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting [30.14175741484625]
  We propose STKAN, a Taylor-nomial forecasting architecture that introduces Kolmogo-Arnold Network modules into spatial and temporal token mixing.<n>Experiments show that STKAN achieves better than evaluated spatial interactions benchmarks on five settings tested.<n>These results suggest that the design of nonlinear function approximators can serve as a useful complement to architectural design in traffic-temporal forecasting.
  arXiv  Detail & Related papers  (2026-07-14T10:18:54Z)
• Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis [48.809049043865905]
  Image deraining plays a pivotal role in low-level computer vision.<n>Deep learning paradigms often suffer from severe performance degradation when generalized to unseen Out-of-Distribution scenarios.<n>This paper proposes a pioneering cross-scenario deraining adaptation framework.
  arXiv  Detail & Related papers  (2026-03-23T07:38:55Z)
• Learn Structure, Adapt on the Fly: Multi-Scale Residual Learning and Online Adaptation for Aerial Manipulators [2.376629619475859]
  Autonomous Aerial Manipulators (AAMs) are inherently coupled, nonlinear systems that exhibit nonstationary and multiscale residual dynamics.<n>We propose a predictive-adaptive framework for real-time residual modeling and compensation in AAMs.
  arXiv  Detail & Related papers  (2026-03-12T08:02:43Z)
• Time-Delayed Transformers for Data-Driven Modeling of Low-Dimensional Dynamics [0.0]
  We present a time-delayed transformer (TD-TF) for data-driven modeling of unsteady-temporal dynamics.<n>The architecture is deliberately minimal, consisting of one self-attention layer with a single query per generalization and one feedforward layer.<n> Numerical experiments demonstrate that TD-TF matches the performance of strong linear baselines on near-linear systems, while significantly outperforming them in nonlinear and chaotic regimes.
  arXiv  Detail & Related papers  (2026-02-09T10:22:43Z)
• LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation [44.62533878314138]
  Localized Semantic Alignment (LSA) is a framework for fine-tuning pre-trained video generation models.<n>LSA enhances temporal consistency by aligning semantic features between ground-truth and generated video clips.<n> experiments on nuScenes and KITTI datasets show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2026-02-05T18:21:02Z)
• Learning solution operator of dynamical systems with diffusion maps kernel ridge regression [2.7802667650114485]
  We show that a simple kernel ridge regression (KRR) framework provides a strong baseline for long-term prediction of complex dynamical systems.<n>Across a broad range of systems, DM-KRR consistently outperforms state-of-the-art random feature, neural-network and operator-learning methods in both accuracy and data efficiency.
  arXiv  Detail & Related papers  (2025-12-19T03:29:23Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• Time Extrapolation with Graph Convolutional Autoencoder and Tensor Train Decomposition [9.446359051690292]
  We develop a time-consistent reduced-order model for parameterized partial differential equations on unstructured grids.<n>In particular, high-fidelity snapshots are represented as a combination of parametric, spatial, and temporal cores via TT decomposition.<n>We enhance the generalization performance by developing a multi-fidelity two-stages approach in the framework of Deep Operator Networks (DeepONet)<n> Numerical results, including heat-conduction, advection-diffusion and vortex-shedding phenomena, demonstrate great performance in effectively learning the dynamic in the extrapolation regime for complex geometries.
  arXiv  Detail & Related papers  (2025-11-28T09:59:17Z)
• Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching [16.17115009663765]
  We introduce textbfPAFM, a framework that models perturbed trajectories to ensure stable and structurally consistent time series generation.<n>The framework incorporates perturbation-guided training to simulate localized disturbances and leverages a dual-path velocity field to capture trajectory deviations under perturbation.<n>In experiments on both unconditional and conditional generation tasks, PAFM consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-11-18T13:30:56Z)
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter [42.60778405812048]
  We introduce FNF as the backbone and DBD as architecture to provide excellent learning capabilities and optimal learning pathways for spatial-temporal modeling.<n>We show that FNF unifies local time-domain and global frequency-domain information processing within a single backbone that extends naturally to spatial modeling.
  arXiv  Detail & Related papers  (2025-06-10T18:40:20Z)
• MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting [51.94256702463408]
  Time series predictability is derived from periodic characteristics at different frequencies.<n>We propose a novel time series forecasting method based on multi-frequency reference series correlation analysis.<n> Experiments on major open and synthetic datasets show state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-11T11:40:14Z)
• AverageTime: Enhance Long-Term Time Series Forecasting with Simple Averaging [6.125620036017928]
  Long-term time series forecasting focuses on leveraging historical data to predict future trends.<n>The core challenge lies in effectively modeling dependencies both within sequences and channels.<n>Our research proposes a new approach for capturing sequence and channel dependencies: AverageTime.
  arXiv  Detail & Related papers  (2024-12-30T05:56:25Z)
• DA-Flow: Dual Attention Normalizing Flow for Skeleton-based Video Anomaly Detection [52.74152717667157]
  We propose a lightweight module called Dual Attention Module (DAM) for capturing cross-dimension interaction relationships in-temporal skeletal data. It employs the frame attention mechanism to identify the most significant frames and the skeleton attention mechanism to capture broader relationships across fixed partitions with minimal parameters and flops.
  arXiv  Detail & Related papers  (2024-06-05T06:18:03Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• Rough Transformers for Continuous and Efficient Time-Series Modelling [46.58170057001437]
  Time-series data in real-world medical settings typically exhibit long-range dependencies and are observed at non-uniform intervals. We introduce the Rough Transformer, a variation of the Transformer model which operates on continuous-time representations of input sequences. We find that Rough Transformers consistently outperform their vanilla attention counterparts while obtaining the benefits of Neural ODE-based models.
  arXiv  Detail & Related papers  (2024-03-15T13:29:45Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• 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)
• Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System [46.39662315849883]
  We introduce CLMFormer, a novel framework that mitigates redundancy through curriculum learning and a memory-driven decoder.<n>CLMFormer consistently improves Transformer-based models by up to 30%, demonstrating its effectiveness in long-horizon forecasting.
  arXiv  Detail & Related papers  (2022-07-16T04:05:15Z)
• Stacking VAE with Graph Neural Networks for Effective and Interpretable Time Series Anomaly Detection [5.935707085640394]
  We propose a stacking variational auto-encoder (VAE) model with graph neural networks for the effective and interpretable time-series anomaly detection. We show that our proposed model outperforms the strong baselines on three public datasets with considerable improvements.
  arXiv  Detail & Related papers  (2021-05-18T09:50:00Z)

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.