Corpus ID: 221447632

Overcoming Negative Transfer: A Survey

  title={Overcoming Negative Transfer: A Survey},
  author={W. Zhang and Lingfei Deng and D. Wu},
  • W. Zhang, Lingfei Deng, D. Wu
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Transfer learning aims to help the target task with little or no training data by leveraging knowledge from one or multi-related auxiliary tasks. In practice, the success of transfer learning is not always guaranteed, negative transfer is a long-standing problem in transfer learning literature, which has been well recognized within the transfer learning community. How to overcome negative transfer has been studied for a long time and has raised increasing attention in recent years. Thus, it is… CONTINUE READING

    Figures and Tables from this paper.


    Publications referenced by this paper.
    Boosting for transfer learning with multiple sources
    • 273
    • PDF
    A Survey on Transfer Learning
    • 8,879
    • PDF
    Domain Adaptation via Transfer Component Analysis
    • 1,025
    • Highly Influential
    • PDF
    A Survey on Deep Transfer Learning
    • 297
    • PDF
    Adaptive Transfer Learning
    • 72
    • PDF
    Learning Transferable Features with Deep Adaptation Networks
    • 1,635
    • PDF
    Characterizing and Avoiding Negative Transfer
    • 35
    • Highly Influential
    • PDF
    Boosting for transfer learning
    • 1,171
    • Highly Influential
    • PDF