# Random Projection Forest Initialization for Graph Convolutional Networks

## TL;DR

This paper introduces a novel graph initialization method for GCNs using random projection forest, which assigns variable edge weights and improves learning performance over traditional k-NN graphs.

## Contribution

It proposes using rpForest for graph initialization in GCNs, allowing for weighted edges and enhanced learning, with spectral analysis guiding hyperparameter selection.

## Key findings

- rpForest-based initialization outperforms k-NN in experiments
- Variable edge weights improve GCN learning
- Spectral analysis aids hyperparameter tuning

## Abstract

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.