Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College

TL;DR

This paper introduces ELCO, a heuristic semi-supervised graph augmentation method inspired by the Electoral College, which expands training data with high-quality generated nodes and edges to improve graph learning models.

Contribution

The paper proposes a novel graph augmentation technique, ELCO, that automatically generates additional nodes and edges to enhance semi-supervised graph learning.

Findings

ELCO significantly improves model performance by an average of 4.7 points.

ELCO outperforms existing state-of-the-art methods across multiple datasets.

The method is effective with popular GCN and GAT models.

Abstract

Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups. For better model performance, previous studies learn to transform the topology of the input graph. However, these works only focus on optimizing the original nodes and edges, leaving the direction of augmenting existing data unexplored. In this paper, by simulating the generation process of graph signals, we propose a novel heuristic pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. Substantially enlarging the original training set with high-quality generated labeled data, our framework can effectively benefit downstream models. To justify the generality and practicality of ELCO, we couple it with the popular Graph Convolution Network and Graph Attention Network to perform extensive evaluations on three standard datasets. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art. We release our code and data on https://github.com/RingBDStack/ELCO to guarantee reproducibility.