Search Results for author:
Found 3 papers, 1 papers with code
On the Initialization of Graph Neural Networks
In this paper, we analyze the variance of forward and backward propagation across GNN layers and show that the variance instability of GNN initializations comes from the combined effect of the activation function, hidden dimension, graph structure and message passing.
Structured Graph Variational Autoencoders for Indoor Furniture layout Generation
The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph.
Network In Graph Neural Network
However, wider hidden layers can easily lead to overfitting, and incrementally adding more GNN layers can potentially result in over-smoothing. In this paper, we present a model-agnostic methodology, namely Network In Graph Neural Network (NGNN ), that allows arbitrary GNN models to increase their model capacity by making the model deeper.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
