Multiple methods of finding the vertices belonging to a planted dense subgraph in a random dense $G(n, p)$ graph have been proposed, with an emphasis on planted cliques. Such methods can identify the planted subgraph in polynomial time, but are all limited to several subgraph structures. Here, we present PYGON, a graph neural network-based algorithm, which is insensitive to the structure of the planted subgraph. This is the first algorithm that uses advanced learning tools for recovering dense subgraphs. We show that PYGON can recover cliques of sizes $\Theta\left(\sqrt{n}\right)$, where $n$ is the size of the background graph, comparable with the state of the art. We also show that the same algorithm can recover multiple other planted subgraphs of size $\Theta\left(\sqrt{n}\right)$, in both directed and undirected graphs. We suggest a conjecture that no polynomial time PAC-learning algorithm can detect planted dense subgraphs with size smaller than $O\left(\sqrt{n}\right)$, even if in principle one could find dense subgraphs of logarithmic size.
翻译:在随机稠密的 $G (n, p) 图表中,建议采用多种方法查找属于一个种植密度大的子图的脊椎,重点是种植的芯片。这些方法可以识别多元时间的种植的脊椎,但都限于几个子结构。在这里,我们提出PYGON,一个基于神经网络的图形算法,这个算法对种植的子图的结构不敏感。这是第一个使用高级学习工具来回收密度大的子图的算法。我们表明,PYGON可以回收大小为$Theta\left(sqrt{n ⁇ right) 的cliquenquen,其中美元是背景图的大小,与艺术的状态相当。我们还表明,同样的算法可以在直图和无方向的图表中回收多个大小为$theta\left(sqrt{n ⁇ right) 的配置的子图。我们建议,如果在 $O\\rft\\\\\\\\\ log iroma 的子图中找到一个小于 irmacroom 的大小的话,那么 lats,那么 lats lats orts lats lats lats,那么 lats lats latic lats lats lats latimas labs latimas labs labs) labs labs latics latimas latim) 。