{
  "id": "2107.10663",
  "version": "v1",
  "published": "2021-07-21T14:40:14.000Z",
  "updated": "2021-07-21T14:40:14.000Z",
  "title": "Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning",
  "authors": [
    "Naichen Shi",
    "Fan Lai",
    "Raed Al Kontar",
    "Mosharaf Chowdhury"
  ],
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "In this paper we propose Fed-ensemble: a simple approach that bringsmodel ensembling to federated learning (FL). Instead of aggregating localmodels to update a single global model, Fed-ensemble uses random permutations to update a group of K models and then obtains predictions through model averaging. Fed-ensemble can be readily utilized within established FL methods and does not impose a computational overhead as it only requires one of the K models to be sent to a client in each communication round. Theoretically, we show that predictions on newdata from all K models belong to the same predictive posterior distribution under a neural tangent kernel regime. This result in turn sheds light onthe generalization advantages of model averaging. We also illustrate thatFed-ensemble has an elegant Bayesian interpretation. Empirical results show that our model has superior performance over several FL algorithms,on a wide range of data sets, and excels in heterogeneous settings often encountered in FL applications.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-07-21T14:40:14.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "federated learning",
      "improving generalization",
      "model ensembling",
      "sheds light onthe generalization advantages",
      "fed-ensemble"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}