Unsupervised (or self-supervised) graph representation learning is essential to facilitate various graph data mining tasks when external supervision is unavailable. The challenge is to encode the information about the graph structure and the attributes associated with the nodes and edges into a low dimensional space. Most existing unsupervised methods promote similar representations across nodes that are topologically close. Recently, it was shown that leveraging additional graph-level information, e.g., information that is shared among all nodes, encourages the representations to be mindful of the global properties of the graph, which greatly improves their quality. However, in most graphs, there is significantly more structure that can be captured, e.g., nodes tend to belong to (multiple) clusters that represent structurally similar nodes. Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content. These clusters are computed by a differentiable K-means method and are jointly optimized by maximizing the mutual information between nodes of the same clusters. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality. Experiments show that GIC outperforms state-of-art methods in various downstream tasks (node classification, link prediction, and node clustering) with a 0.9% to 6.1% gain over the best competing approach, on average.

翻译：无监督(或自我监督)图形代表性学习对于在外部监管不可用时便利各种图形数据挖掘任务至关重要。 挑战在于将图形结构以及与节点和边缘相关属性的信息编码成一个低维空间。 大多数现有的未监督方法促进在表层接近的节点上类似的表达方式。 最近, 显示利用更多的图层一级信息, 例如所有节点共享的信息, 鼓励演示方注意图表的全球特性, 从而大大提高其质量。 然而, 在大多数图表中, 能够捕捉的架构要大得多, 例如, 节点往往属于代表结构相似节点的( 多面) 组群。 受此观察的驱动, 我们提议了一个图形代表学习方法, 即“ 图形Infoclust”(GIC), 以额外的方式获取集级信息内容。 这些组群群通过不同的K- 比例方法进行计算, 并通过最大限度地利用同一节点之间的相互信息进行优化。 然而, 节点往往属于代表结构相似节点的( 多面) 组群组群, 。 这种优化导致( 多端点) 类群点的群点的类群点的群集的群点的群集的群集显示, 更接近性化, 更甚的群集, 更甚的群集, 更甚的群集, 更甚的群块化, 更甚的群集, 更甚的群块化, 更甚的群集, 更甚的群块化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化的群化的群化的群化的群化的群化的群化的群化的群化的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化, 更甚的群化的群化的群化的群化, 更甚的群化的群化的群化的群化