AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

14 Aug 2019Ke SunZhouchen LinZhanxing Zhu

The design of deep graph models still remains to be investigated and the crucial part is how to explore and exploit the knowledge from different hops of neighbors in an efficient way. In this paper, we propose a novel RNN-like deep graph neural network architecture by incorporating AdaBoost into the computation of network; and the proposed graph convolutional network called AdaGCN~(AdaBoosting Graph Convolutional Network) has the ability to efficiently extract knowledge from high-order neighbors and integrate knowledge from different hops of neighbors into the network in an AdaBoost way... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Evaluation Results from the Paper


 SOTA for Node Classification on Citeseer (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Node Classification Citeseer AdaGCN Accuracy 76.22% # 1
Node Classification Cora AdaGCN Accuracy 85.46% # 5
Node Classification MS ACADEMIC AdaGCN Accuracy 92.87% # 3
Node Classification MS ACADEMIC APPNP (AdaGCN authors) Accuracy 92.98% # 2
Node Classification Pubmed AdaGCN Accuracy 79.76% # 12