2 Related Work
meta-learners方式: 典型代表是, Mishra et al. (2017) used Temporal Convolutions which are deep recurrent networks based on dilated convolutions(扩张卷积), this method also exploits contextual information from the subset T providing very good results.
deep learning architectures on graph-structured data领域: Graph neural networks(GNN) are in fact natural generalizations of convolutional networks to non-Euclidean graphs. 推荐阅读: We refer the reader to Bronstein et al. (2017) for an exhaustive literature review on the topic.
3 PROBLEM SET-UP
We consider input-output pairs (Ti, Yi)i drawn iid from a distribution P of partially-labeled image collections:
![](https://i-blog.csdnimg.cn/blog_migrate/ff1b0219764253775f2668cc8c5fa754.webp?x-image-process=image/format,png)
其中, s 即有label的样本数,r 即无label的样本数,t即待分类的样本数,K即分类类别数。
We will focus in the case t = 1 where we just classify one sample per task T .
Few-Shot Learning: When r = 0, t = 1 and s = qK, there is a single image in the collection with unknown label. If moreover each label appears exactly q times, this setting is referred as the q-shot, K-way learning.
4 MODEL
we associate T with a fully-connected graph GT = (V,E) where nodes va ∈ V correspond to the images present in T (both labeled and unlabeled). In this context, the setup does not specify a fixed similarity ea,a′ between images xa and xa′ , suggesting an approach where this similarity measure is learnt in a discriminative fashion with a parametric model similarly as in Gilmer et al. (2017), such as a siamese neural architecture. This framework is cl