{
  "id": "1905.12665",
  "version": "v1",
  "published": "2019-05-29T18:20:47.000Z",
  "updated": "2019-05-29T18:20:47.000Z",
  "title": "Graph Learning Network: A Structure Learning Algorithm",
  "authors": [
    "Darwin Saire Pilco",
    "Adín Ramírez Rivera"
  ],
  "comment": "Accepted for publication at ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data. Code available at https://gitlab.com/mipl/graph-learning-network",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Recently, graph neural networks (GNNs) has proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static relationships. We propose the Graph Learning Network (GLN), a simple yet effective process to learn node embeddings and structure prediction functions. Our model uses graph convolutions to propose expected node features, and predict the best structure based on them. We repeat these steps recursively to enhance the prediction and the embeddings.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-05-29T18:20:47.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "graph learning network",
      "structure learning algorithm",
      "learn node embeddings",
      "structure prediction functions",
      "graph neural networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}