DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecasting

• URL: http://arxiv.org/abs/2604.23968v1
• Date: Mon, 27 Apr 2026 02:29:35 GMT
• Title: DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecasting
• Abstract summary: DecompKAN is a lightweight attention-free architecture that combines trend-residual decomposition, channel-wise patching, learned instance normalization, and B-spline Kolmogorov-Arnold Network (KAN) edge functions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate time series forecasting in scientific domains such as climate modeling, physiological monitoring, and energy systems benefits from both competitive predictions and model transparency. This work proposes DecompKAN, a lightweight attention-free architecture that combines trend-residual decomposition, channel-wise patching, learned instance normalization, and B-spline Kolmogorov-Arnold Network (KAN) edge functions. Each KAN edge learns an explicit, inspectable 1D scalar function over learned patch-embedding coordinates that can be directly visualized. On standard benchmarks, DecompKAN achieves best or tied-best MSE on 15 of 32 dataset-horizon combinations among selected published baselines, and achieves best or tied-best MSE on 20 of 36 comparisons under a controlled same-recipe evaluation across 9 datasets including the physiological PPG-DaLiA benchmark. The architecture shows particular strength on datasets with smooth temporal dynamics (Solar -17%, ECL -10% vs. iTransformer, Weather) and physiological time series. Visualization of learned edge functions reveals qualitatively different latent nonlinearities across domains. Ablation analysis shows that the architectural pipeline (decomposition, patching, normalization) drives performance more than the choice of nonlinear layer, while the KAN formulation enables inspection of learned latent transformations.

Related papers

• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification [52.452902154360565]
  CuBAS is an information-geometric framework for adaptive data selection in supervised classification.<n>A labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geometric complexity of the data distribution.
  arXiv  Detail & Related papers  (2026-07-03T09:36:02Z)
• Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA [0.0]
  We propose a domain-informed representation learning framework for irregular astronomical time series.<n>We combine semantics-preserving views, uncertainty-aware tokenization, and multi-view self-distillation.<n>Our model outperforms hand-crafted features on 15 of 16 classification metrics.
  arXiv  Detail & Related papers  (2026-06-26T08:35:55Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• INDEQS: Informed Neural controlled Differential EQuationS [13.60302952986747]
  We introduce Informed Informed Neural controlled Differential EQuationS (INDEQS), a graph-based NCDE forecasting method.<n>INDEQS separates inner mixing of hidden states across graph nodes from outer mixing between vector field and control.<n>We evaluate INDEQS on two real-world tasks: river discharge forecasting on a hydrological network and traffic flow prediction on PeMS08.
  arXiv  Detail & Related papers  (2026-06-17T14:46:23Z)
• The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning [14.724143004818961]
  In this work, we identify intrinsic geometry as a key latent factor governing model effectiveness.<n>We introduce a curvature-stratified evaluation framework that partitions datasets into positive, negative, and near-zero curvature regimes.<n>We find that model rankings are highly stable within each curvature regime but shift significantly across regimes, indicating that performance is fundamentally geometry-dependent.
  arXiv  Detail & Related papers  (2026-06-04T17:05:36Z)
• Differentiable latent structure discovery for interpretable forecasting in clinical time series [38.473526928012724]
  We introduce StructGP, a continuous-time multi-task Gaussian process that couples differentiable structure learning to uncover a sparse, ordered directed acyclic graph (DAG) of inter-variable dependencies while preserving principled uncertainty.<n>We propose LP-StructGP, which augments StructGP with latent pathways-shared, temporally shifted trajectories inferred via subject-specific coupling filters and a softmax gating mechanism-to capture cross-patient progression patterns.
  arXiv  Detail & Related papers  (2026-04-30T14:59:50Z)
• Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting [52.53742727060265]
  Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets.<n>Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3Dwin UNet backbone of the pioneering model.<n>We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data.<n>Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2026-04-20T11:40:39Z)
• Depth Completion as Parameter-Efficient Test-Time Adaptation [66.72360181325877]
  CAPA is a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion.<n>For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency.
  arXiv  Detail & Related papers  (2026-02-16T13:53:23Z)
• Structural Compositional Function Networks: Interpretable Functional Compositions for Tabular Discovery [4.8369208007394215]
  We propose Structural Compositional Networks ( StructuralCFN), a novel architecture that imposes a Relation-Aware Inductive Bias via a differentiable structural prior.<n>Our framework enables Structured Knowledge Integration, allowing domain-specific relational priors to be injected directly into the architecture to guide discovery.<n>We evaluate StructuralCFN across a rigorous 10-fold cross-validation suite on 18 benchmarks, demonstrating statistically significant improvements.
  arXiv  Detail & Related papers  (2026-01-27T20:20:07Z)
• PCR-ORB: Enhanced ORB-SLAM3 with Point Cloud Refinement Using Deep Learning-Based Dynamic Object Filtering [0.0]
  ORB-SLAM3 framework integrates deep learning-based point cloud refinement to mitigate dynamic object interference.<n>YOLOv8 semantic segmentation combined with ground-accelerated processing to achieve real-time performance.
  arXiv  Detail & Related papers  (2025-12-29T09:10:31Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• 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)
• Inter-layer Transition in Neural Architecture Search [89.00449751022771]
  The dependency between the architecture weights of connected edges is explicitly modeled in this paper. Experiments on five benchmarks confirm the value of modeling inter-layer dependency and demonstrate the proposed method outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-30T03:33:52Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)

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.