Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College
This addresses the challenge of data scarcity in graph-based semi-supervised learning, offering a practical solution for improving model performance in domains like social networks or bioinformatics, though it is incremental as it builds on existing graph transformation methods.
The paper tackles the problem of limited labeled data in semi-supervised graph learning by proposing ELCO, a heuristic pre-processing technique that generates new nodes and edges to expand the training set, boosting the average score of base models by 4.7 points and outperforming state-of-the-art methods.
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.