论文标题
MLANE：基于元学习的自适应网络嵌入
MLANE: Meta-Learning Based Adaptive Network Embedding
论文作者
论文摘要
大多数现有的随机步行网络嵌入方法通常仅遵循同义或结构等效性的两个原则之一。然而，在现实世界网络中，节点表现出同质和结构等效性的混合物，这需要自适应网络嵌入，可以适应不同节点分析任务中不同节点的同质和结构对等。在本文中，我们提出了一种称为基于元学习的自适应网络嵌入（MLANE）的新方法，该方法可以通过将嵌入学习嵌入到一个优化问题中，可以通过端对端末端的元学习框架来解决不同任务中的不同节点的自适应采样策略。在对实际数据集的广泛实验中，MLANE显示了基线的显着性能改善。 MLANE的源代码和实验中使用的数据集以及基线的所有超参数设置，请访问https://github.com/77333com/mlane。
Most existing random walk based network embedding methods often follow only one of two principles, homophily or structural equivalence. In real world networks, however, nodes exhibit a mixture of homophily and structural equivalence, which requires adaptive network embedding that can adaptively preserve both homophily and structural equivalence for different nodes in different down-stream analysis tasks. In this paper, we propose a novel method called Meta-Learning based Adaptive Network Embedding (MLANE), which can learn adaptive sampling strategy for different nodes in different tasks by incorporating sampling strategy learning with embedding learning into one optimization problem that can be solved via an end-to-end meta-learning framework. In extensive experiments on real datasets, MLANE shows significant performance improvements over the baselines. The source code of MLANE and the datasets used in experiments and all the hyperparameter settings for baselines are available at https://github.com/7733com/MLANE.
