{
  "id": "1912.10206",
  "version": "v1",
  "published": "2019-12-21T05:56:15.000Z",
  "updated": "2019-12-21T05:56:15.000Z",
  "title": "How Robust Are Graph Neural Networks to Structural Noise?",
  "authors": [
    "James Fox",
    "Sivasankaran Rajamanickam"
  ],
  "comment": "Accepted workshop paper at Deep Learning on Graphs: Methodologies and Applications (DLGMA'20)",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "Graph neural networks (GNNs) are an emerging model for learning graph embeddings and making predictions on graph structured data. However, robustness of graph neural networks is not yet well-understood. In this work, we focus on node structural identity predictions, where a representative GNN model is able to achieve near-perfect accuracy. We also show that the same GNN model is not robust to addition of structural noise, through a controlled dataset and set of experiments. Finally, we show that under the right conditions, graph-augmented training is capable of significantly improving robustness to structural noise.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-12-21T05:56:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "graph neural networks",
      "structural noise",
      "node structural identity predictions",
      "achieve near-perfect accuracy",
      "graph structured data"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}