{
  "abstract": "Self-supervised representation learning from unlabeled channel state information (CSI) can reduce labeling and adaptation overhead in learning-based multiple-input multiple-output (MIMO) systems. Existing CSI pretraining methods typically use reconstruction objectives or contrastive pairs from generic augmentations, which do not explicitly reflect transmission-relevant channel similarity. This paper proposes beam-response contrastive learning (BRCL), a self-supervised CSI pretraining framework based on the transmit-side Gram matrix. For a channel matrix $\\mathbf{H}$, $\\mathbf{R}=\\mathbf{H}^{\\mathrm{H}}\\mathbf{H}$ determines the received power of any unit-norm transmit beam $\\mathbf{w}$ as $|\\mathbf{H}\\mathbf{w}|_2^2=\\mathbf{w}^{\\mathrm{H}}\\mathbf{R}\\mathbf{w}$. BRCL maps each CSI sample to a beam-response profile and uses the induced soft similarity as a label-free relational target for contrastive pretraining. Combined with reconstruction learning, BRCL enforces both sample-level CSI recovery and beam-response-level consistency, yielding transferable CSI representations without task-specific labels or manual positive pairs. Experiments on diverse MIMO channel datasets show that BRCL improves label efficiency and outperforms autoencoder- and channel-charting-based pretraining across beam selection, user selection, and future beam selection tasks.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2607.24872",
  "author_total": 5,
  "authors": [
    {
      "name": "Sehyun Ryu"
    },
    {
      "name": "Yumin Kim"
    },
    {
      "name": "Minjae Lee"
    },
    {
      "name": "Hyun Jong Yang"
    },
    {
      "name": "John M. Cioffi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0f8q25svqkcf7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2607.24872",
  "fulltext_url": null,
  "id": "0f8q25svqkcf7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2607.24872",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.SY"
    ],
    [
      "arxiv",
      "eess.SY"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "2208|Millimeter-Wave Propagation and Modeling"
    ]
  ],
  "openalex": "W7171743078",
  "pdf_url": "https://arxiv.org/pdf/2607.24872",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0f8q25svqkcf7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:57Z",
      "native_id": "2607.24872",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2607.24872"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "Self-Supervised Pretraining for Transmission-Relevant MIMO CSI Representation",
  "title_text": "Self-Supervised Pretraining for Transmission-Relevant MIMO CSI Representation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:57Z",
  "url": "https://research.draconitic.com/paper/0f8q25svqkcf7",
  "venue": "arXiv",
  "versions": []
}