Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains

• URL: http://arxiv.org/abs/2607.02055v1
• Date: Thu, 02 Jul 2026 11:32:38 GMT
• Title: Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains
• Abstract summary: 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.
• Score: 1.8595194352358455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption often breaks down in spatiotemporally correlated domains such as aerial surveillance, precision agriculture, and medical imaging, leading to two systematic failures: data leakage, where correlated samples span training and validation splits and inflate performance estimates, and hidden stratification, where errors on minority subpopulations are obscured by aggregate metrics. To address these issues, we propose a unified evaluation and training framework for spatially correlated data. We introduce Structure-Aware Stratified Partitioning (SASP), which constructs validation splits that reduce spatiotemporal leakage while preserving meaningful class balance, and Curriculum Distributionally Robust Optimization (CDRO), a curriculum-based relaxation of distributionally robust training that stabilizes optimization under these stricter splits. Across multiple benchmarks, this combination yields consistently improved generalization, more reliable confidence calibration, and exposes failure modes that remain hidden under conventional random-split evaluation.

Related papers

• ControlledShifts: Towards Standardizing Robustness Evaluation in Trajectory Prediction Under Distribution Shifts [12.370065954075299]
  Trajectory prediction is central to safety in autonomous driving.<n>Many methods attempt to mitigate distribution shift degradation through data-centric or test-time adaptation approaches.<n>We introduce ControlledShifts, a framework that systematically re-splits existing trajectory datasets into in-distribution and out-of-distribution partitions.
  arXiv  Detail & Related papers  (2026-08-18T15:16:52Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Forecasting Multivariate Time Series under Predictive Heterogeneity: A Validation-Driven Clustering Framework [8.124770608442377]
  We formulate adaptive pooling as a statistical decision problem.<n>We propose a validation-driven framework that determines when and how specialization should be applied.<n> Experiments on large-scale traffic datasets demonstrate consistent improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-04-15T11:35:32Z)
• Modest-Align: Data-Efficient Alignment for Vision-Language Models [67.48633659305592]
  Cross-modal alignment models often suffer from overconfidence and degraded performance when operating in resource-constrained settings.<n>We propose Modest-Align, a lightweight alignment framework designed for robustness and efficiency.<n>Our method offers a practical and scalable solution for cross-modal alignment in real-world, low-resource scenarios.
  arXiv  Detail & Related papers  (2025-10-24T16:11:10Z)
• Distributionally Robust Federated Learning with Outlier Resilience [8.69285602685459]
  We study distributionally robust federated learning with explicit outlier resilience.<n>We reformulate the problem as a tractable Lagrangian penalty optimization, which admits robustness certificates.<n>Building on this reformulation, we propose the distributionally outlier-robust federated learning algorithm and establish its convergence guarantees.
  arXiv  Detail & Related papers  (2025-09-29T08:42:12Z)
• Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Data [49.36938105983916]
  Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data.<n>We propose incorporating multi-scale feature extraction and uncertainty estimation to improve the model's generalization and robustness across domains.
  arXiv  Detail & Related papers  (2025-08-26T03:13:08Z)
• CoCAI: Copula-based Conformal Anomaly Identification for Multivariate Time-Series [0.3495246564946556]
  We propose a novel framework that harnesses the power of generative artificial intelligence and copula-based modeling to deliver accurate predictions and enable robust anomaly detection.
  arXiv  Detail & Related papers  (2025-07-23T14:15:31Z)
• Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls [8.720733751119994]
  We study the underlying optimization problem, develop efficient solution algorithms, and demonstrate that the proposed method outperforms benchmark approaches on standard datasets.<n>Inspired by the former, we study the Wasserstein DR counterpart of ARO for logistic regression and show it admits a tractable convex optimization reformulation.
  arXiv  Detail & Related papers  (2024-07-18T15:59:37Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Global Distance-distributions Separation for Unsupervised Person Re-identification [93.39253443415392]
  Existing unsupervised ReID approaches often fail in correctly identifying the positive samples and negative samples through the distance-based matching/ranking. We introduce a global distance-distributions separation constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view. We show that our method leads to significant improvement over the baselines and achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-01T07:05:39Z)

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.