AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

Abstract

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 of current nodes and then integrates knowledge from different hops of neighbors into the network in an Adaboost way. Different from other graph neural networks that directly stack many graph convolution layers, AdaGCN shares the same base neural network architecture among all ``layers'' and is recursively optimized, which is similar to an RNN. Besides, We also theoretically established the connection between AdaGCN and existing graph convolutional methods, presenting the benefits of our proposal. Finally, extensive experiments demonstrate the consistent state-of-the-art prediction performance on graphs across different label rates and the computational advantage of our approach AdaGCN~\footnote{Code is available at \url{https://github.com/datake/AdaGCN}.}

Published on International Conference on Learning Representations (ICLR) 2021

References in corpus (6)

• Simplifying Graph Convolutional Networks
• Towards Deeper Graph Neural Networks
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Greedy Layerwise Learning Can Scale to ImageNet

Cited by in corpus (11)

• Heterogeneous Deep Graph Infomax
• Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework
• NodeNet: A Graph Regularised Neural Network for Node Classification
• Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
• Topological Regularization for Graph Neural Networks Augmentation
• Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification
• Graph Neural Distance Metric Learning with Graph-Bert
• G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
• Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features