{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.11997",
  "author_total": 3,
  "authors": [
    {
      "name": "Wenrui Xu"
    },
    {
      "name": "Anas Enanaa"
    },
    {
      "name": "Keshab K. Parhi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f655476xd2577.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.11997",
  "fulltext_url": null,
  "id": "f655476xd2577",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.11997",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1711|Time Series Analysis and Forecasting"
    ]
  ],
  "openalex": "W7212929187",
  "pdf_url": "https://arxiv.org/pdf/2609.11997",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f655476xd2577.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:17Z",
      "native_id": "2609.11997",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.11997"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning",
  "title_text": "DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:17Z",
  "url": "https://research.draconitic.com/paper/f655476xd2577",
  "venue": "arXiv",
  "versions": []
}