Corpus ID: 231718648

Combat Data Shift in Few-shot Learning with Knowledge Graph

@article{Zhu2021CombatDS,
  title={Combat Data Shift in Few-shot Learning with Knowledge Graph},
  author={Yongchun Zhu and Fuzhen Zhuang and X. Zhang and Zhiyuan Qi and Zhiping Shi and Q. He},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.11354}
}
Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 62 REFERENCES
Meta-Transfer Learning for Few-Shot Learning
  • 247
  • PDF
Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
  • 4
  • PDF
TADAM: Task dependent adaptive metric for improved few-shot learning
  • 424
  • PDF
LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning
  • 28
  • PDF
Domain Adaption in One-Shot Learning
  • 24
  • PDF
Learning to Compare: Relation Network for Few-Shot Learning
  • 1,166
  • Highly Influential
  • PDF
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
  • 57
  • PDF
Optimization as a Model for Few-Shot Learning
  • 1,522
MetaGAN: An Adversarial Approach to Few-Shot Learning
  • 134
  • PDF
A Closer Look at Few-shot Classification
  • 447
  • PDF
...
1
2
3
4
5
...