On the choice of graph neural network architectures
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the development of graph networks, this setup has become a de facto benchmark for a significant body of research. Interestingly, several works have recently shown that in this particular setting, graph neural networks do not perform much better than predefined low-pass filters followed by a linear classifier. However, when learning from little data in a high-dimensional space, it is not surprising that simple and heavily regularized methods are near-optimal. In this paper, we show empirically that in settings with fewer features and more training data, more complex graph networks significantly outperform simple models, and propose a few insights towards the proper choice of graph network architectures. We finally outline the importance of using sufficiently diverse benchmarks (including lower dimensional signals as well) when designing and studying new types of graph neural networks.
Code (2)
Tasks
Graph Neural NetworkNode ClassificationSimilar Papers 제목 키워드 기반
From Message-Passing to Linearized Graph Sequence Models
Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of modern deep learning architectures in other domains, particularly sequenc…
Graph LearningOn the Expressive Power of Graph Neural Networks
The study of Graph Neural Networks has received considerable interest in the past few years. By extending deep learning to graph-structured data, GNNs can solve a diverse set of tasks in fields including social science, …
Graph ClassificationAlternative Graph Neural Networks: Synergizing GEV Models and Deep Learning for Travel Mode Choice Modeling
Generalized extreme value models capture dependence among choice alternatives in discrete choice modeling, but require this dependence to be predefined, symmetric, and shared uniformly across individuals. Recent efforts …
Autobahn: Automorphism-based Graph Neural Nets
We introduce Automorphism-based graph neural networks (Autobahn), a new family of graph neural networks. In an Autobahn, we decompose the graph into a collection of subgraphs and apply local convolutions that are equivar…
Graph Neural NetworkGraphs for deep learning representations
In recent years, Deep Learning methods have achieved state of the art performance in a vast range of machine learning tasks, including image classification and multilingual automatic text translation. These architectures…
BIG-bench Machine LearningDeep Learningimage-classificationImage Classification+1