Improving Graph Neural Networks with Simple Architecture Design

05/17/2021
by   Sunil Kumar Maurya, et al.
0

Graph Neural Networks have emerged as a useful tool to learn on the data by applying additional constraints based on the graph structure. These graphs are often created with assumed intrinsic relations between the entities. In recent years, there have been tremendous improvements in the architecture design, pushing the performance up in various prediction tasks. In general, these neural architectures combine layer depth and node feature aggregation steps. This makes it challenging to analyze the importance of features at various hops and the expressiveness of the neural network layers. As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction tasks without any prior information. In this work, we decouple the node feature aggregation step and depth of graph neural network and introduce several key design strategies for graph neural networks. More specifically, we propose to use softmax as a regularizer and "Soft-Selector" of features aggregated from neighbors at different hop distances; and "Hop-Normalization" over GNN layers. Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64 tasks. Moreover, analyzing the learned soft-selection parameters of the model provides a simple way to study the importance of features in the prediction tasks. Finally, we demonstrate with experiments that the model is scalable for large graphs with millions of nodes and billions of edges.

READ FULL TEXT

page 6

page 7

research
11/12/2021

Simplifying approach to Node Classification in Graph Neural Networks

Graph Neural Networks have become one of the indispensable tools to lear...
research
10/02/2020

Efficient Colon Cancer Grading with Graph Neural Networks

Dealing with the application of grading colorectal cancer images, this w...
research
05/07/2021

Hierarchical Graph Neural Networks

Over the recent years, Graph Neural Networks have become increasingly po...
research
06/17/2016

Most central or least central? How much modeling decisions influence a node's centrality ranking in multiplex networks

To understand a node's centrality in a multiplex network, its centrality...
research
10/08/2022

Break the Wall Between Homophily and Heterophily for Graph Representation Learning

Homophily and heterophily are intrinsic properties of graphs that descri...
research
08/20/2021

TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction

Tabular data prediction (TDP) is one of the most popular industrial appl...
research
08/24/2019

Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks

In this study, we propose a novel graph neural network, called propagate...

Please sign up or login with your details

Forgot password? Click here to reset