{
  "id": "1908.09963",
  "version": "v1",
  "published": "2019-08-27T00:20:48.000Z",
  "updated": "2019-08-27T00:20:48.000Z",
  "title": "Deep-Learning Based Linear Average Consensus for Faster Convergence over Temporal Network",
  "authors": [
    "Masako Kishida",
    "Masaki Ogura",
    "Tadashi Wadayama"
  ],
  "categories": [
    "math.OC"
  ],
  "abstract": "In this paper, we study the problem of accelerating the linear average consensus algorithm over complex networks. We specifically present a data-driven methodology for tuning the weights of temporal (i.e., time-varying) networks by using deep learning techniques. We first unfold the linear average consensus protocol to obtain a feedforward signal flow graph, which we regard as a neural network. We then train the neural network by using standard deep learning technique to minimize the consensus error over a given finite time-horizon. As a result of the training, we obtain a set of optimized time-varying weights for faster consensus in the network. Numerical simulations are presented to show that our methodology can achieve a significantly smaller consensus error than the static optimal strategy.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-08-27T00:20:48.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "faster convergence",
      "temporal network",
      "deep learning technique",
      "linear average consensus protocol",
      "linear average consensus algorithm"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}