论文标题
金属：通过元学习在图表上的主动半监督学习
MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
论文作者
论文摘要
主动学习的目的（AL）是通过仅选择最有用的标签实例来培训具有较少标记实例的分类模型。为其他数据类型（例如图像和文本）设计的AL算法在图形结构数据上表现不佳。尽管已经提出了一些基于启发式的AL算法用于图形，但缺乏一种原则性的方法。在本文中，我们提出了一种金属，一种AL方法，它选择了未标记的实例，可以直接改善分类模型的未来性能。对于半监督的学习问题，我们将AL任务作为双层优化问题。根据元学习的最新工作，我们使用元梯度来近似使用任何未标记实例对模型性能进行重新验证的影响。使用属于不同域的多个图形数据集，我们证明了金属有效地优于现有的最新算法。
The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and text do not perform well on graph-structured data. Although a few heuristics-based AL algorithms have been proposed for graphs, a principled approach is lacking. In this paper, we propose MetAL, an AL approach that selects unlabeled instances that directly improve the future performance of a classification model. For a semi-supervised learning problem, we formulate the AL task as a bilevel optimization problem. Based on recent work in meta-learning, we use the meta-gradients to approximate the impact of retraining the model with any unlabeled instance on the model performance. Using multiple graph datasets belonging to different domains, we demonstrate that MetAL efficiently outperforms existing state-of-the-art AL algorithms.
