Combat Data Shift in Few-shot Learning with Knowledge Graph. (arXiv:2101.11354v3 [cs.LG] UPDATED)

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 various data distributions. Most existing
few-shot learning approaches are …

arxiv data few-shot learning graph knowledge graph learning