{
  "id": "1806.01547",
  "version": "v1",
  "published": "2018-06-05T08:23:42.000Z",
  "updated": "2018-06-05T08:23:42.000Z",
  "title": "ClusterNet : Semi-Supervised Clustering using Neural Networks",
  "authors": [
    "Ankita Shukla",
    "Gullal Singh Cheema",
    "Saket Anand"
  ],
  "comment": "9 Pages",
  "categories": [
    "cs.LG",
    "cs.CV",
    "stat.ML"
  ],
  "abstract": "Clustering using neural networks has recently demon- strated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learn- ing or their dependence on large set of labeled data sam- ples. In this paper, we propose ClusterNet that uses pair- wise semantic constraints from very few labeled data sam- ples (< 5% of total data) and exploits the abundant un- labeled data to drive the clustering approach. We define a new loss function that uses pairwise semantic similarity between objects combined with constrained k-means clus- tering to efficiently utilize both labeled and unlabeled data in the same framework. The proposed network uses con- volution autoencoder to learn a latent representation that groups data into k specified clusters, while also learning the cluster centers simultaneously. We evaluate and com- pare the performance of ClusterNet on several datasets and state of the art deep clustering approaches.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-06-05T08:23:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural networks",
      "clusternet",
      "labeled data",
      "semi-supervised clustering",
      "performance"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 9,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}