论文标题
学习推断知识：跨传输几声遥远链接预测
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
论文作者
论文摘要
许多实用的图形问题，例如知识图构建和药物 - 药物相互作用预测，都需要处理多关系图。但是，使用图形神经网络（GNN）处理现实世界的多关系图通常是由于其不断发展的性质而具有挑战性的，因为新实体（节点）随着时间的推移会出现。此外，新出现的实体通常几乎没有链接，这使学习变得更加困难。在这一挑战的推动下，我们引入了一个现实的问题，即几乎没有拼图链接预测，我们不仅可以预测所见和看不见的节点之间的链接，就像传统的知识范围内链接预测任务一样，而且在看不见的节点之间，每个节点只有很少的边缘。我们通过一种新型的跨传输元学习框架来解决这个问题，我们称之为图外推网（Gen）。 Gen Meta-learns均用于归纳推理的节点嵌入网络（可见的无偿）和链接预测网络（未看到的to-Unseen）。对于转导链接预测，我们进一步提出了一个随机嵌入层，以模拟看不见的实体之间的链接预测中的不确定性。我们在多个基准数据集上验证我们的模型，以进行知识图完成和药物毒品相互作用预测。结果表明，我们的模型大大胜过相关的基线，用于隔壁链接预测任务。
Many practical graph problems, such as knowledge graph construction and drug-drug interaction prediction, require to handle multi-relational graphs. However, handling real-world multi-relational graphs with Graph Neural Networks (GNNs) is often challenging due to their evolving nature, as new entities (nodes) can emerge over time. Moreover, newly emerged entities often have few links, which makes the learning even more difficult. Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction task but also between the unseen nodes, with only few edges per node. We tackle this problem with a novel transductive meta-learning framework which we refer to as Graph Extrapolation Networks (GEN). GEN meta-learns both the node embedding network for inductive inference (seen-to-unseen) and the link prediction network for transductive inference (unseen-to-unseen). For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction. The results show that our model significantly outperforms relevant baselines for out-of-graph link prediction tasks.
