Graph deep learning: State of the art and challenges
The last half-decade has seen a surge in deep learning research on irregular domains and
efforts to extend convolutional neural networks (CNNs) to work on irregularly structured data …
efforts to extend convolutional neural networks (CNNs) to work on irregularly structured data …
Deep graph generators: A survey
Deep generative models have achieved great success in areas such as image, speech, and
natural language processing in the past few years. Thanks to the advances in graph-based …
natural language processing in the past few years. Thanks to the advances in graph-based …
Information-based Gradient enhanced Causal Learning Graph Neural Network for fault diagnosis of complex industrial processes
By representing the embedded components and their interactions in industrial systems as
nodes and edges in a graph, Graph Neural Networks (GNNs) have achieved outstanding …
nodes and edges in a graph, Graph Neural Networks (GNNs) have achieved outstanding …
Reinforcement learning for adaptive mesh refinement
Finite element simulations of physical systems governed by partial differential equations
(PDE) crucially depend on adaptive mesh refinement (AMR) to allocate computational …
(PDE) crucially depend on adaptive mesh refinement (AMR) to allocate computational …
Goal-directed graph construction using reinforcement learning
VA Darvariu, S Hailes… - Proceedings of the …, 2021 - royalsocietypublishing.org
Graphs can be used to represent and reason about systems and a variety of metrics have
been devised to quantify their global characteristics. However, little is currently known about …
been devised to quantify their global characteristics. However, little is currently known about …
Purify and generate: Learning faithful item-to-item graph from noisy user-item interaction behaviors
Matching is almost the first and most fundamental step in recommender systems, that is to
quickly select hundreds or thousands of related entities from the whole commodity pool …
quickly select hundreds or thousands of related entities from the whole commodity pool …
KPG: Key Propagation Graph Generator for Rumor Detection based on Reinforcement Learning
The proliferation of rumors on social media platforms during significant events, such as the
US elections and the COVID-19 pandemic, has a profound impact on social stability and …
US elections and the COVID-19 pandemic, has a profound impact on social stability and …
Self-supervised Subgraph Neural Network With Deep Reinforcement Walk Exploration
J Huang, H Kasai - arxiv preprint arxiv:2502.01809, 2025 - arxiv.org
Graph data, with its structurally variable nature, represents complex real-world phenomena
like chemical compounds, protein structures, and social networks. Traditional Graph Neural …
like chemical compounds, protein structures, and social networks. Traditional Graph Neural …
Learning to boost resilience of complex networks via neural edge rewiring
The resilience of complex networks refers to their ability to maintain functionality in the face
of structural attacks. This ability can be improved by performing minimal modifications to the …
of structural attacks. This ability can be improved by performing minimal modifications to the …
[PDF][PDF] A Twist for Graph Classification: Optimizing Causal Information Flow in Graph Neural Networks
Z Zhao13, P Wang12, H Wen, Y Zhang, Z Zhou12… - 2024 - ustc.edu.cn
Graph neural networks (GNNs) have achieved state-of-theart results on many graph
representation learning tasks by exploiting statistical correlations. However, numerous …
representation learning tasks by exploiting statistical correlations. However, numerous …