Results 261 to 270 of about 7,952,537 (299)

A Survey of Dynamic Graph Neural Networks [PDF]

open access: yesFrontiers of Computer Science
Abstract Graph neural networks (GNNs) have emerged as a powerful tool for effectively mining and learning from graph-structured data, with applications spanning numerous domains. However, most research focuses on static graphs, neglecting the dynamic nature of real-world networks where topologies and attributes evolve over time.
Yanping Zheng
exaly   +6 more sources

Robust Knowledge Adaptation for Dynamic Graph Neural Networks [PDF]

open access: yesIEEE Transactions on Knowledge and Data Engineering
Graph structured data often possess dynamic characters in nature. Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling graph data. However, almost all existing approaches operate under the assumption that, upon the establishment of a new link, the embeddings of the neighboring nodes should undergo ...
Guoren Wang, Ye Yuan, Hongyuan Zha
exaly   +5 more sources

Pre-Training on Dynamic Graph Neural Networks

open access: yesNeurocomputing, 2022
The pre-training on the graph neural network model can learn the general features of large-scale networks or networks of the same type by self-supervised methods, which allows the model to work even when node labels are missing. However, the existing pre-training methods do not take network evolution into consideration.
Ke-Jia Chen, Yunyun Wang, Yuxuan Dai
exaly   +5 more sources

SDG: A Simplified and Dynamic Graph Neural Network

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in many high-impact applications such as fraud detection, information retrieval, and recommender systems due to their powerful representation learning capabilities. Some nascent efforts have been concentrated on simplifying the structures of GNN models, in order to reduce the ...
Dongqi Fu, Jingrui He
openaire   +1 more source

EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs

Proceedings of the ACM on Management of Data, 2023
Graph neural networks have been widely used to learn node representations for many real-world static graphs. In general, they learn node representations by recursively aggregating information from neighbors. However, graphs in many applications are dynamic, evolving with continuous graph events, such as node feature and graph structure updates.
Haoyang Li 0002, Lei Chen 0002
openaire   +1 more source

Dynamic Spiking Graph Neural Networks

Proceedings of the AAAI Conference on Artificial Intelligence
The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs. However, as a common problem, dynamic graph representation learning faces challenges such as high complexity and large ...
Nan Yin   +5 more
openaire   +3 more sources

Dynamics of neural networks over undirected graphs

Neural Networks, 2015
In this paper we study the dynamical behavior of neural networks such that their interconnections are the incidence matrix of an undirected finite graph G=(V,E) (i.e., the weights belong to {0,1}). The network may be updated synchronously (every node is updated at the same time), sequentially (nodes are updated one by one in a prescribed order) or in a
Eric Goles Ch., Gonzalo A. Ruz
openaire   +2 more sources

Dynamic Local Filters in Graph Convolutional Neural Networks

2023
Over the last few years, we have seen increasing data generated from non-Euclidean domains, usually represented as graphs with complex relationships. Graph Neural Networks (GNN) have gained a high interest because of their potential in processing graph-structured data.
Andrea Apicella 0001   +3 more
openaire   +3 more sources

Graph neural networks for molecular dynamics simulations

Current Opinion in Structural Biology
Graph neural networks (GNNs) are emerging as powerful tools for advancing molecular dynamics (MD) simulations, providing data-driven frameworks to complement traditional physics-based approaches. By representing atoms and their interactions as graphs, GNNs naturally encode chemical and structural information, enabling accurate neural network force ...
Mohd Ahsan   +4 more
openaire   +2 more sources

Dynamic Gated Graph Neural Networks for Scene Graph Generation

2019
We describe a new deep generative architecture, called Dynamic Gated Graph Neural Networks (D-GGNN), for extracting a scene graph for an image, given a set of bounding-box proposals. A scene graph is a visually-grounded digraph for an image, where the nodes represent the objects and the edges show the relationships between them.
Mahmoud Khademi, Oliver Schulte
openaire   +1 more source

Home - About - Disclaimer - Privacy