{
  "id": "2308.04762",
  "version": "v1",
  "published": "2023-08-09T07:51:07.000Z",
  "updated": "2023-08-09T07:51:07.000Z",
  "title": "Tram-FL: Routing-based Model Training for Decentralized Federated Learning",
  "authors": [
    "Kota Maejima",
    "Takayuki Nishio",
    "Asato Yamazaki",
    "Yuko Hara-Azumi"
  ],
  "comment": "This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible",
  "categories": [
    "cs.LG",
    "cs.DC",
    "cs.NI"
  ],
  "abstract": "In decentralized federated learning (DFL), substantial traffic from frequent inter-node communication and non-independent and identically distributed (non-IID) data challenges high-accuracy model acquisition. We propose Tram-FL, a novel DFL method, which progressively refines a global model by transferring it sequentially amongst nodes, rather than by exchanging and aggregating local models. We also introduce a dynamic model routing algorithm for optimal route selection, aimed at enhancing model precision with minimal forwarding. Our experiments using MNIST, CIFAR-10, and IMDb datasets demonstrate that Tram-FL with the proposed routing delivers high model accuracy under non-IID conditions, outperforming baselines while reducing communication costs.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-08-09T07:51:07.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "68T20",
      "68M14",
      "I.2.7",
      "I.2.8"
    ],
    "keywords": [
      "decentralized federated learning",
      "routing-based model training",
      "data challenges high-accuracy model acquisition",
      "routing delivers high model accuracy",
      "novel dfl method"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}