Every node counts: Self-ensembling graph convolutional networks for semi-supervised learning

Highlights：

• To the best of our knowledge, our method (SEGCN) is the first to introduce a teacher-student ensemble strategy in the Graph Convolutional Networks (GCNs) design.

• By proposing to combine the ensemble model with classic GCNs, we em-phasize the importance of exploitation of unlabeled nodes in graph-structured data classification in the context of semi-supervised learning.

• Analogy to the noise added to student model in regular data, we successfully design new perturbation strategies for the graph-based student model.

• We make the t-SNE analysis in latent feature space and observe that SEGCN can generate better embedding representations in latent feature space thus leading to better classification accuracy.

• Our results are on par with the state-of-the-art methods on four node classification benchmarks in terms of accuracy, i.e. Citeseer (69.9% → 73.4%), Core (80.4% → 83.5%), Pubmed (78.6% → 78.9%) and NELL(67.8% → 73.5%).

摘要

•To the best of our knowledge, our method (SEGCN) is the first to introduce a teacher-student ensemble strategy in the Graph Convolutional Networks (GCNs) design.•By proposing to combine the ensemble model with classic GCNs, we em-phasize the importance of exploitation of unlabeled nodes in graph-structured data classification in the context of semi-supervised learning.•Analogy to the noise added to student model in regular data, we successfully design new perturbation strategies for the graph-based student model.•We make the t-SNE analysis in latent feature space and observe that SEGCN can generate better embedding representations in latent feature space thus leading to better classification accuracy.•Our results are on par with the state-of-the-art methods on four node classification benchmarks in terms of accuracy, i.e. Citeseer (69.9% → 73.4%), Core (80.4% → 83.5%), Pubmed (78.6% → 78.9%) and NELL(67.8% → 73.5%).