Graph convolutional networks (GCNs) were a great step towards extending deep learning to unstructured data such as graphs. But GCNs still need a constructed graph to work with. To solve this problem, classical graphs such as $k$-nearest neighbor are usually used to initialize the GCN. Although it is computationally efficient to construct $k$-nn graphs, the constructed graph might not be very useful for learning. In a $k$-nn graph, points are restricted to have a fixed number of edges, and all edges in the graph have equal weights. We present a new way to construct the graph and initialize the GCN. It is based on random projection forest (rpForest). rpForest enables us to assign varying weights on edges indicating varying importance, which enhanced the learning. The number of trees is a hyperparameter in rpForest. We performed spectral analysis to help us setting this parameter in the right range. In the experiments, initializing the GCN using rpForest provides better results compared to $k$-nn initialization.
翻译:图形革命网络( GCN) 是向将深层次学习扩展至无结构化数据( 如图表) 迈出的一大步。 但是, GCN 仍需要一个构建好的图表来解决这个问题。 为了解决这个问题, 通常会使用典型的图形( 如$k$- near near near near near) 来启动 GCN 。 虽然构建的图形在计算上效率上可以构建 $k$- nn 的图形, 但构建的图形对学习可能并不十分有用 。 在 $- nn 的图形中, 点限制为固定的边缘数, 图形中的所有边缘数都具有等量的重量 。 我们提出了构建图形和初始化 GCN 的新方法。 它基于随机投影的森林( rpforest) 。 rpForest 使我们能够在显示不同重要性的边缘上分配不同的重量, 从而增强学习。 树木的数量在 rpforest 中是一个超参数。 我们进行了分析, 以帮助我们在正确的范围内设定这个参数。 在实验中, 使用 rpFest 提供比 $- nn intfest 更好的结果 。