A comprehensive survey on graph neural networks

Z Wu, S Pan, F Chen, G Long, C Zhang… - IEEE transactions on …, 2020‏ - ieeexplore.ieee.org
Deep learning has revolutionized many machine learning tasks in recent years, ranging
from image classification and video processing to speech recognition and natural language …

[HTML][HTML] Graph neural networks: A review of methods and applications

J Zhou, G Cui, S Hu, Z Zhang, C Yang, Z Liu, L Wang… - AI open, 2020‏ - Elsevier
Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

How powerful are graph neural networks?

K Xu, W Hu, J Leskovec, S Jegelka - arxiv preprint arxiv:1810.00826, 2018‏ - arxiv.org
Graph Neural Networks (GNNs) are an effective framework for representation learning of
graphs. GNNs follow a neighborhood aggregation scheme, where the representation vector …

Weisfeiler and leman go neural: Higher-order graph neural networks

C Morris, M Ritzert, M Fey, WL Hamilton… - Proceedings of the …, 2019‏ - ojs.aaai.org
In recent years, graph neural networks (GNNs) have emerged as a powerful neural
architecture to learn vector representations of nodes and graphs in a supervised, end-to-end …

Reinforcement learning for solving the vehicle routing problem

M Nazari, A Oroojlooy, L Snyder… - Advances in neural …, 2018‏ - proceedings.neurips.cc
We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using
reinforcement learning. In this approach, we train a single policy model that finds near …

Computing graph neural networks: A survey from algorithms to accelerators

S Abadal, A Jain, R Guirado, J López-Alonso… - ACM Computing …, 2021‏ - dl.acm.org
Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent
years owing to their capability to model and learn from graph-structured data. Such an ability …

Generalization and representational limits of graph neural networks

V Garg, S Jegelka, T Jaakkola - International conference on …, 2020‏ - proceedings.mlr.press
We address two fundamental questions about graph neural networks (GNNs). First, we
prove that several important graph properties, eg, shortest/longest cycle, diameter, or certain …

Graph networks as learnable physics engines for inference and control

A Sanchez-Gonzalez, N Heess… - International …, 2018‏ - proceedings.mlr.press
Understanding and interacting with everyday physical scenes requires rich knowledge
about the structure of the world, represented either implicitly in a value or policy function, or …

Dual encoder-based dynamic-channel graph convolutional network with edge enhancement for retinal vessel segmentation

Y Li, Y Zhang, W Cui, B Lei, X Kuang… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Retinal vessel segmentation with deep learning technology is a crucial auxiliary method for
clinicians to diagnose fundus diseases. However, the deep learning approaches inevitably …

What can neural networks reason about?

K Xu, J Li, M Zhang, SS Du, K Kawarabayashi… - arxiv preprint arxiv …, 2019‏ - arxiv.org
Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require
specialized network structures, eg, Graph Neural Networks (GNNs) perform well on many …