Graph Meta Learning via Local Subgraphs
Graph Meta Learning via Local Subgraphs
复制标题
DOI：
--
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Kexin Huang;M. Zitnik
中科院分区：
文献类型：
--
作者：
Kexin Huang;M. Zitnik
目前流行的图学习方法需要大量的标签和边信息来学习。当新任务的数据稀缺时，元学习可以从以前的经验中学习，并形成急需的归纳偏见，以便快速适应新任务。在这里，我们介绍了一种新的图的元学习算法G-Meta。G-Meta使用局部子图传递特定于子图的信息，并通过元梯度更快地学习可转移知识。G-Meta学习如何仅使用新任务中的少数节点或边来快速适应新任务，并通过学习其他图或相关标签集中的数据点来做到这一点。G-Meta在理论上是合理的，因为我们证明了预测的证据可以在目标节点或边周围的局部子图中找到。在7个数据集和9个基线方法上的实验表明，G-Meta算法的性能比现有方法高出16.3%。与以前的方法不同，G-Meta成功地在具有挑战性的、不太可能的学习环境中学习，这些学习环境需要将其推广到全新的图形和从未见过的标签。最后，G-Meta可扩展到大型图，我们在一个包含1,840个图的新生命树数据集上进行了演示，比以前工作中使用的图的数量增加了两个数量级。
Prevailing methods for graphs require abundant label and edge information for learning. When data for a new task are scarce, meta-learning can learn from prior experiences and form much-needed inductive biases for fast adaption to new tasks. Here, we introduce G-Meta, a novel meta-learning algorithm for graphs. G-Meta uses local subgraphs to transfer subgraph-specific information and learn transferable knowledge faster via meta gradients. G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets. G-Meta is theoretically justified as we show that the evidence for a prediction can be found in the local subgraph surrounding the target node or edge. Experiments on seven datasets and nine baseline methods show that G-Meta outperforms existing methods by up to 16.3%. Unlike previous methods, G-Meta successfully learns in challenging, few-shot learning settings that require generalization to completely new graphs and never-before-seen labels. Finally, G-Meta scales to large graphs, which we demonstrate on a new Tree-of-Life dataset comprising of 1,840 graphs, a two-orders of magnitude increase in the number of graphs used in prior work.