{
  "id": "2201.09202",
  "version": "v1",
  "published": "2022-01-23T07:19:11.000Z",
  "updated": "2022-01-23T07:19:11.000Z",
  "title": "One-Shot Learning on Attributed Sequences",
  "authors": [
    "Zhongfang Zhuang",
    "Xiangnan Kong",
    "Elke Rundensteiner",
    "Aditya Arora",
    "Jihane Zouaoui"
  ],
  "doi": "10.1109/BigData.2018.8622257",
  "categories": [
    "cs.LG",
    "cs.AI"
  ],
  "abstract": "One-shot learning has become an important research topic in the last decade with many real-world applications. The goal of one-shot learning is to classify unlabeled instances when there is only one labeled example per class. Conventional problem setting of one-shot learning mainly focuses on the data that is already in feature space (such as images). However, the data instances in real-world applications are often more complex and feature vectors may not be available. In this paper, we study the problem of one-shot learning on attributed sequences, where each instance is composed of a set of attributes (e.g., user profile) and a sequence of categorical items (e.g., clickstream). This problem is important for a variety of real-world applications ranging from fraud prevention to network intrusion detection. This problem is more challenging than conventional one-shot learning since there are dependencies between attributes and sequences. We design a deep learning framework OLAS to tackle this problem. The proposed OLAS utilizes a twin network to generalize the features from pairwise attributed sequence examples. Empirical results on real-world datasets demonstrate the proposed OLAS can outperform the state-of-the-art methods under a rich variety of parameter settings.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-01-23T07:19:11.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "one-shot learning",
      "real-world applications",
      "real-world datasets demonstrate",
      "deep learning framework olas",
      "important research topic"
    ],
    "tags": [
      "journal article"
    ],
    "publication": {
      "publisher": "IEEE"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}