论文标题
识别和减轻退化核心嵌入中的不稳定性
Identifying and Mitigating Instability in Embeddings of the Degenerate Core
论文作者
论文摘要
图形的退化核心稳定的嵌入方式是吗？当我们系统地删除外围节点（通过重复剥离$ k $ - 库）时，节点的嵌入在退化核心中会发生什么？我们发现了三种模式W.R.T.跨多个流行的嵌入算法和数据集的流行图中的退化核心嵌入中的不稳定性。我们使用回归来量化图嵌入稳定性中的变更点。此外，我们提出了稳定的算法，该算法采用了嵌入算法并使其稳定的现有图。我们在使退化核心嵌入稳定且仍在产生最先进的链路预测性能方面表明了稳定的有效性。
Are the embeddings of a graph's degenerate core stable? What happens to the embeddings of nodes in the degenerate core as we systematically remove periphery nodes (by repeated peeling off $k$-cores)? We discover three patterns w.r.t. instability in degenerate-core embeddings across a variety of popular graph embedding algorithms and datasets. We use regression to quantify the change point in graph embedding stability. Furthermore, we present the STABLE algorithm, which takes an existing graph embedding algorithm and makes it stable. We show the effectiveness of STABLE in terms of making the degenerate-core embedding stable and still producing state-of-the-art link prediction performance.
