DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning

• URL: http://arxiv.org/abs/2609.11997v1
• Date: Wed, 09 Sep 2026 22:52:37 GMT
• Title: DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
• Abstract summary: We propose a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning.<n>DCRA produces more balanced and structured representations compared to baseline and diffusion-only models.
• Score: 7.328100870402178
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Learning robust representations for time-series signals under noise and distribution shifts remains challenging, especially in clinical applications such as electroencephalogram (EEG) and electrocardiogram (ECG) analysis. We propose Diffusion-Conditioned Representation Alignment (DCRA), a training framework that repurposes the forward diffusion process as a structured corruption scheduler for representation learning. Different from conventional augmentation and consistency-based methods that rely on independently sampled perturbations, DCRA introduces a structured corruption trajectory via the diffusion forward process, which enables continuous and controlled representation evolution across noise levels. We introduce a feature-level consistency objective that aligns representations across noise levels while preserving class-discriminative structure. This mechanism promotes structure-preserving consistency, which enables smooth and semantically coherent feature trajectories in latent space. The proposed framework is encoder-agnostic and can be integrated with state space models and Transformer architectures. The seizure detection experiments on the CHB-MIT EEG dataset show that DCRA consistently improves performance under multiple noise conditions and achieves higher sensitivity at low false-positive rates. Analysis reveals that DCRA produces more balanced and structured representations compared to baseline and diffusion-only models. These findings highlight the benefit of combining structured corruption with representation alignment for robust time-series learning.

Related papers

• Hierarchical Policy Learning via Spectral Decomposition [58.65543693788772]
  We identify a semantic decomposition in robot action sequences, separating task-level motion intent from execution-level refinements.<n>Motivated by this structure, we propose Causal Spectral Policy (CSP), which models action generation as a causal coarse-to-fine process.<n>CSP consistently outperforms strong baselines on precision-sensitive manipulation tasks.
  arXiv  Detail & Related papers  (2026-06-28T19:22:40Z)
• Effective Covariance Dynamics in Solvable High-Dimensional GANs [2.639628765667673]
  We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspace from data.<n>We prove that the microscopic training process converges, in the high-dimensional limit, to deterministic ordinary differential equations governed by this effective covariance.
  arXiv  Detail & Related papers  (2026-06-25T16:33:54Z)
• On the Redundancy of Timestep Embeddings in Diffusion Models [3.0458514384586404]
  Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales.<n>We provide a theoretical framework demonstrating that, under certain conditions, the global minimizer of the diffusion training objective can be achieved without explicit timestep conditioning.<n>Our analysis suggests these architectures can implicitly infer noise scales from the corrupted input under specific assumptions, rendering explicit temporal conditioning redundant.
  arXiv  Detail & Related papers  (2026-06-18T16:01:39Z)
• RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval [24.383054290279173]
  RankVR is a framework designed to construct a robust Composed Image Retrieval model via global structure consistency and dynamic value perception.<n>It significantly outperforms existing state-of-the-art methods, validating its superior robustness in noisy environments.
  arXiv  Detail & Related papers  (2026-06-10T06:06:34Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• 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)
• WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records [1.585843510099207]
  WISTERIA is a weakly supervised representation learning framework.<n>It learns representations by enforcing consistency across their induced label distributions.<n>It improves predictive performance across standard EHR benchmarks.
  arXiv  Detail & Related papers  (2026-05-10T21:25:41Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• A Representation-Consistent Gated Recurrent Framework for Robust Medical Time-Series Classification [0.0]
  We propose a representation-consistent gated recurrent framework (RC-GRF) that introduces a principled regularization strategy to enforce temporal consistency in hidden-state representations.<n>The proposed framework is model-agnostic and can be integrated into existing gated recurrent architectures without modifying their internal gating mechanisms.
  arXiv  Detail & Related papers  (2026-02-10T17:16:49Z)
• DiffRegCD: Integrated Registration and Change Detection with Diffusion Features [74.3102451211493]
  We present DiffRegCD, an integrated framework that unifies dense registration and change detection in a single model.<n>Experiments on aerial (LEVIR-CD, DSIFN-CD, WHU-CD, SYSU-CD) and ground level (VL-CMU-CD) datasets show that DiffRegCD consistently surpasses recent baselines.
  arXiv  Detail & Related papers  (2025-11-11T07:32:19Z)
• Learning Robust Diffusion Models from Imprecise Supervision [75.53546939251146]
  DMIS is a unified framework for training robust Conditional Diffusion Models from Imprecise Supervision.<n>Our framework is derived from likelihood and decomposes the objective into generative and classification components.<n>Experiments on diverse forms of imprecise supervision, covering tasks covering image generation, weakly supervised learning, and dataset condensation demonstrate that DMIS consistently produces high-quality and class-discriminative samples.
  arXiv  Detail & Related papers  (2025-10-03T14:00:32Z)
• Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application [11.385703484113552]
  We propose a novel semantic communication framework empowered by generative artificial intelligence (GAI)<n>A latent diffusion model (LDM)-based semantic communication framework is proposed that combines a variational autoencoder for semantic features extraction.<n>The proposed system is a training-free framework that supports zero-shot generalization, and achieves superior performance under low-SNR and out-of-distribution conditions.
  arXiv  Detail & Related papers  (2025-06-06T03:20:32Z)

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.