Improving the Long-Range Performance of Gated Graph Neural Networks

2020/07/19 by Denis Lukovnikov, Jens Lehmann, Lukovnikov, Denis +3 · 1 citation
Computer Science · Engineering · Mathematics · #Advanced Graph Neural Networks #Architecture #Artificial intelligence #Artificial neural network #Computer network #Computer science #Data mining #Deep neural networks #Engineering #FOS: Computer and information sciences #Graph #Graph Theory and Algorithms #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Network architecture #Range (aeronautics) #Theoretical computer science #Topic Modeling #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2007.09668

published in arXiv (Cornell University) (Cornell University)

arxiv created 2020/07/19 · openalex publication_date 2020/07/19 · arxiv updated 2020/07/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• On the difficulty of training Recurrent Neural Networks
• Gated Graph Sequence Neural Networks
• Neural Message Passing for Quantum Chemistry

Cited by

• On Measuring Long-Range Interactions in Graph Neural Networks

Related

• GraphMinNet: Learning Dependencies in Graphs with Light Complexity Minimal Architecture
• NDGGNET-A Node Independent Gate based Graph Neural Networks
• Graph Neural Networks: Architectures, Stability and Transferability
• Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
• A Survey on The Expressive Power of Graph Neural Networks