Improving the Long-Range Performance of Gated Graph Neural Networks
arXiv:2007.09668
Abstract
Many popular variants of graph neural networks (GNNs) that are capable of handling multi-relational graphs may suffer from vanishing gradients. In this work, we propose a novel GNN architecture based on the Gated Graph Neural Network with an improved ability to handle long-range dependencies in multi-relational graphs. An experimental analysis on different synthetic tasks demonstrates that the proposed architecture outperforms several popular GNN models.
References in corpus (8)
- Neural Message Passing for Quantum Chemistry
- On the difficulty of training Recurrent Neural Networks
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Gated Graph Sequence Neural Networks
- Relational Graph Attention Networks
- On the Bottleneck of Graph Neural Networks and its Practical Implications
- Revisiting Over-smoothing in Deep GCNs
- Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing