Skip to main content

Call for Papers: Special Issue on Representation Learning for Big Data Analytics

1. Summary and Scope

In this era of big data, we have witnessed a dramatic growth in the volume, variety and complexity of data, including textual, imaging, video and time sequence datasets. These large scale and heterogeneous data arise from multiple sources and applications.  Significant challenges therefore arise for the design of effective, scalable algorithms and generalized frameworks to meet the multiple requirements of real-world tasks, e.g. understanding, recognition and control. Representation learning is a key component of various intelligent data analytic algorithms, with its capacity to discover the intrinsic structure of data. Consequently, it has become critical to explore advanced representation learning techniques for large scale and heterogeneous data analytics.

This timely special issue serves as an interdisciplinary forum for researchers across the world to share their findings in this exciting area. We solicit original contributions on machine learning theories, deep learning models, surveys of recent advances, benchmark datasets and novel application scenarios. 

The topics include but are not limited to:

  • Scalable optimization algorithms for representation learning
  • Unsupervised, semi-supervised, and supervised learning (either shallow or deep) with representation learning for big data analytics
  • Representation learning in neural architecture search, deep network compression
  • Representation learning in zero-shot learning, few-shot learning
  • Representation learning in retrieval and recommendation systems for big data analytics
  • Representation learning in large scale object detection, recognition, and tracking, semantic segmentation
  • Representation learning in transfer learning and multi-modal learning
  • Representation learning in graph embedding, graph neural networks, manifold learning
  • Representation learning in natural language processing and question answering
  • Novel datasets and benchmarks for big data analytics
  • Implementation issues, parallelization, software platforms, hardware for representation learning
  • Other related topics of representation learning

2. Submission Guidelines
Authors should prepare their manuscripts according to the submission guidelines of “Big Data Analytics” outlined at the journal website All papers will be peer-reviewed following a regular reviewing procedure. Each submission should clearly demonstrate evidence of benefits to society or large communities. Originality and impact, in combination with an innovative technical aspect of the proposed algorithms/datasets/applications will be the major evaluation criteria.

3. Important Dates
Submissions are open until the end of 2020. However potential authors are highly encouraged to submit papers to the special issue as early as possible. Papers will be reviewed and processed as soon as they are submitted.

4. Guest Editors

Annual journal metrics

  • Speed
    122.2 days to first decision for reviewed manuscripts only
    106.9 days to first decision for all manuscripts
    278.5 days from submission to acceptance
    25 days from acceptance to publication

    8 Altmetric mentions