Rethinking Time Series Domain Generalization via Structure-Stratified Calibration

• URL: http://arxiv.org/abs/2603.02756v1
• Date: Tue, 03 Mar 2026 08:55:22 GMT
• Title: Rethinking Time Series Domain Generalization via Structure-Stratified Calibration
• Abstract summary: In real-world settings, datasets often originate from structurally heterogeneous families of dynamical systems.<n>We propose a structurally stratified calibration framework that distinguishes structurally consistent samples and performs amplitude calibration exclusively within structurally compatible sample clusters.
• Score: 2.194820012814419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For time series arising from latent dynamical systems, existing cross-domain generalization methods commonly assume that samples are comparably meaningful within a shared representation space. In real-world settings, however, different datasets often originate from structurally heterogeneous families of dynamical systems, leading to fundamentally distinct feature distributions. Under such circumstances, performing global alignment while neglecting structural differences is highly prone to establishing spurious correspondences and inducing negative transfer. From the new perspective of cross-domain structural correspondence failure, we revisit this problem and propose a structurally stratified calibration framework. This approach explicitly distinguishes structurally consistent samples and performs amplitude calibration exclusively within structurally compatible sample clusters, thereby effectively alleviating generalization failures caused by structural incompatibility. Notably, the proposed framework achieves substantial performance improvements through a concise and computationally efficient calibration strategy. Evaluations on 19 public datasets (100.3k samples) demonstrate that SSCF significantly outperforms strong baselines under the zero-shot setting. These results confirm that establishing structural consistency prior to alignment constitutes a more reliable and effective pathway for improving cross-domain generalization of time series governed by latent dynamical systems.

Related papers

• Structure Learning on Clustered Data [2.1095754823099657]
  We introduce a new approach that estimates a global structure while accounting for local cluster-level effects.<n>We present a differentiable graph coupling mechanism that guarantees the union of the fixed- and random-effects graphs remains acyclic.
  arXiv  Detail & Related papers  (2026-07-09T08:35:30Z)
• Imputation Meets Clustering: Exploiting Latent Subgroup Structure for Missing Data Recovery [52.29866804948133]
  We propose CAGI (Cluster-Aware Generative Imputation), a framework that reformulates clustering and imputation as a mutually reinforcing co-optimization process.<n>Experiments on 14 benchmark datasets with 15 representative baselines demonstrate the superiority of CAGI.
  arXiv  Detail & Related papers  (2026-07-08T02:50:02Z)
• Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy [57.058369251551795]
  Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks.<n>We propose SCISE, a framework that preserves structural Integrity by synergizing community-aware sampling with constrained Structural Entropy.<n>We show that SCISE significantly outperforms state-of-the-art algorithms, with ablation studies and robustness analyses further validating its effectiveness and reliability for real-world large-scale graphs.
  arXiv  Detail & Related papers  (2026-07-06T07:55:53Z)
• Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains [1.8595194352358455]
  We propose a unified evaluation and training framework for spatially correlated data.<n>We show that this combination yields consistently improved generalization, more reliable confidence calibration, and exposes modes failure that remain hidden under conventional random-split evaluation.
  arXiv  Detail & Related papers  (2026-07-02T11:32:38Z)
• Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection [1.5439079597766574]
  We study the role of the inference stride, which controls whether subsequences are processed as disjoint windows or with overlap.<n>We propose a unified training, tuning, and multi-seed evaluation protocol on the curated TSB-AD benchmark.<n>We show that overlapping windows yield consistent improvements, with average relative gain up to +28%, and can alter method rankings.
  arXiv  Detail & Related papers  (2026-06-02T19:42:30Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding [36.012422604739236]
  We propose Structure-Aware Domain Generalization (SADG), a Mamba-based In-Context Learning framework that preserves structural hierarchy across domains and tasks.<n>SADG uses centroid-based topology and geodesic curvature continuity to generate transformation-invariant sequences.<n>It consistently outperforms state-of-the-art methods across multiple tasks including reconstruction, denoising, and registration.
  arXiv  Detail & Related papers  (2026-03-21T09:55:10Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning [2.152549977410309]
  High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches.<n>Our architecture introduces an adaptive kernel-based attention mechanism that processes distinct feature groups separately before integration.<n> Experimental results show substantial improvements in performance metrics, compared to the state-of-the-art methods across diverse datasets.
  arXiv  Detail & Related papers  (2025-10-18T12:41:18Z)
• An Improved Time Series Anomaly Detection by Applying Structural Similarity [17.056935729423667]
  We propose StrAD, a novel structure-enhanced anomaly detection approach.<n>We show that StrAD improves the performance of state-of-the-art reconstruction-based models across five real-world anomaly detection datasets.
  arXiv  Detail & Related papers  (2025-09-24T14:45:00Z)
• AlphaFold Database Debiasing for Robust Inverse Folding [58.792020809180336]
  We introduce a Debiasing Structure AutoEncoder (DeSAE) that learns to reconstruct native-like conformations from intentionally corrupted backbone geometries.<n>At inference, applying DeSAE to AFDB structures produces debiased structures that significantly improve inverse folding performance.
  arXiv  Detail & Related papers  (2025-06-10T02:25:31Z)
• Persistent Homology for Structural Characterization in Disordered Systems [6.538609026810757]
  We propose a unified framework based on persistent homology (PH) to characterize both local and global structures in disordered systems.<n>It can simultaneously generate local and global descriptors using the same algorithm and data structure.<n>It has shown to be highly effective and interpretable in predicting particle rearrangements and classifying global phases.
  arXiv  Detail & Related papers  (2024-11-21T18:24:06Z)
• Fast and Reliable Probabilistic Reflectometry Inversion with Prior-Amortized Neural Posterior Estimation [73.81105275628751]
  Finding all structures compatible with reflectometry data is computationally prohibitive for standard algorithms. We address this lack of reliability with a probabilistic deep learning method that identifies all realistic structures in seconds. Our method, Prior-Amortized Neural Posterior Estimation (PANPE), combines simulation-based inference with novel adaptive priors.
  arXiv  Detail & Related papers  (2024-07-26T10:29:16Z)
• Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detection [22.005142941322912]
  We propose a new method that combines a neighborhood-driven data augmentation strategy with a multi-manifold representation learning framework.<n>Our method achieves superior performance in terms of both accuracy and robustness, showing strong potential for generalization and real-world deployment.
  arXiv  Detail & Related papers  (2024-05-25T14:48:04Z)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Posterior Differential Regularization with f-divergence for Improving Model Robustness [95.05725916287376]
  We focus on methods that regularize the model posterior difference between clean and noisy inputs. We generalize the posterior differential regularization to the family of $f$-divergences. Our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness.
  arXiv  Detail & Related papers  (2020-10-23T19:58:01Z)
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift [67.57720300323928]
  Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. We propose two methods for automatically constructing ensembles with emphvarying architectures. We show that the resulting ensembles outperform deep ensembles not only in terms of accuracy but also uncertainty calibration and robustness to dataset shift.
  arXiv  Detail & Related papers  (2020-06-15T17:38:15Z)

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.