# Label-Aware Graph Convolutional Networks

## TL;DR

This paper introduces Label-Aware Graph Convolutional Networks (LAGCN), which enhance node classification by explicitly identifying and utilizing valuable neighbors through a label-aware edge classifier, improving existing GCN models without architectural changes.

## Contribution

The paper proposes a label-aware edge classifier to filter and add valuable neighbors, creating a label-aware graph that improves GCN performance without altering their architecture.

## Key findings

- LAGCN significantly improves node classification accuracy.
- The label-aware edge classifier effectively filters distracting neighbors.
- Increasing the positive ratio of valuable neighbors enhances GCN performance.

## Abstract

Recent advances in Graph Convolutional Networks (GCNs) have led to state-of-the-art performance on various graph-related tasks. However, most existing GCN models do not explicitly identify whether all the aggregated neighbors are valuable to the learning tasks, which may harm the learning performance. In this paper, we consider the problem of node classification and propose the Label-Aware Graph Convolutional Network (LAGCN) framework which can directly identify valuable neighbors to enhance the performance of existing GCN models. Our contribution is three-fold. First, we propose a label-aware edge classifier that can filter distracting neighbors and add valuable neighbors for each node to refine the original graph into a label-aware~(LA) graph. Existing GCN models can directly learn from the LA graph to improve the performance without changing their model architectures. Second, we introduce the concept of positive ratio to evaluate the density of valuable neighbors in the LA graph. Theoretical analysis reveals that using the edge classifier to increase the positive ratio can improve the learning performance of existing GCN models. Third, we conduct extensive node classification experiments on benchmark datasets. The results verify that LAGCN can improve the performance of existing GCN models considerably, in terms of node classification.