主动学习少样本图顶点分类，无需预知类别信息。
Active Few-Shot Learning for Vertex Classification Starting from an Unlabeled Dataset
- 迭代询问人工标注者选择顶点标注，逐步放宽假设条件。
- 少样本下原型网络优于GCN，标签少于20时性能更稳定。
- 适用于真实场景中类别未知、标签成本高的图数据任务。
尽管图数据丰富，但获取顶点标签耗时且昂贵。因此，仅用少量标注顶点学习尤为关键。现有少样本学习方法依赖类别预言机（class oracle），可提供目标类别的标注顶点，但在真实场景中无法实现——标注前无法预知顶点所属类别。少样本学习常与原型网络结合，而传统半监督顶点分类使用判别模型如图卷积网络（GCN）。本文提出一种主动学习框架，通过迭代向人工标注者提示待标注顶点。我们进行了三项实验：首先在“均衡采样”中假设存在类别预言机；其次在“非均衡采样”中用k-medoids聚类替代预言机，从簇中选取顶点标注；最后在“未知类别数”实验中不再预设类别数量与分布。结果表明，当每类样本少于20个时，原型网络始终优于判别模型。放弃类别预言机后，GCN性能下降9%，原型网络仅下降1%。在“未知类别数”实验中，两类模型平均性能再降1%。代码已开源。
原文摘要 · Abstract (English)
Despite the ample availability of graph data, obtaining vertex labels is a tedious and expensive task. Therefore, it is desirable to learn from a few labeled vertices only. Existing few-shot learners assume a class oracle, which provides labeled vertices for a desired class. However, such an oracle is not available in a real-world setting, i.e., when drawing a vertex for labeling it is unknown to which class the vertex belongs. Few-shot learners are often combined with prototypical networks, while classical semi-supervised vertex classification uses discriminative models, e.g., Graph Convolutional Networks (GCN). In this paper, we train our models by iteratively prompting a human annotator with vertices to annotate. We perform three experiments where we continually relax our assumptions. First, we assume a class oracle, i.e., the human annotator is provided with an equal number of vertices to label for each class. We denote this as "Balanced Sampling''. In the subsequent experiment, "Unbalanced Sampling,'' we replace the class oracle with $k$-medoids clustering and draw vertices to label from the clusters. In the last experiment, the "Unknown Number of Classes,'' we no longer assumed we knew the number and distribution of classes. Our results show that prototypical models outperform discriminative models in all experiments when fewer than $20$ samples per class are available. While dropping the assumption of the class oracle for the "Unbalanced Sampling'' experiment reduces the performance of the GCN by $9\%$, the prototypical network loses only $1\%$ on average. For the "Unknown Number of Classes'' experiment, the average performance for both models decreased further by $1\%$. Source code: https://github.com/Ximsa/2023-felix-ma
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。