论文标题
角色2VEC：灵活的多角色表示图形的学习框架
Persona2vec: A Flexible Multi-role Representations Learning Framework for Graphs
论文作者
论文摘要
图形嵌入技术学习图的低维表示，正在在许多图挖掘任务中实现最先进的性能。大多数现有的嵌入算法为每个节点分配一个向量，隐含地假设单个表示足以捕获节点的所有特征。但是，在许多领域中，通常观察到大多数节点都属于多个社区的社区结构，这是通常的，取决于上下文，扮演着不同的角色。在这里，我们提出了persona2vec，这是一个图形嵌入框架，该框架可以根据其结构上下文有效地学习节点的多个表示。使用基于链接预测的评估，我们表明我们的框架要比现有的最新模型快得多，同时实现了更好的性能。
Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we propose persona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance.
