Results 61 to 70 of about 36,148 (258)

Degree-Aware Graph Neural Network Quantization

Entropy, 2023
In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges.
Ziqin Fan, Xi Jin
doaj   +1 more source

Gated Graph Convolutional Recurrent Neural Networks [PDF]

2019 27th European Signal Processing Conference (EUSIPCO), 2019
Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems.
Luana Ruiz, Fernando Gama, Alejandro Ribeiro   +2 more
openaire   +2 more sources

Advancing Lithium–Oxygen Batteries: Pioneering Cathode Catalyst Innovation and Artificial Intelligence‐Driven Design Paradigms

Advanced Materials, EarlyView.
This review summarizes the principles and challenges of nonaqueous lithium‐oxygen batteries and recent advances in cathode catalysts, including carbon‐based materials, metals, oxides, sulfides, nitrides, carbides, and redox mediators. It highlights emerging design strategies and artificial intelligence‐driven approaches, emphasizing data‐assisted ...
Yuqing Yao, Chongyang Hao, Karol Viviana Mejia‐Centeno, Malik Dilshad Khan, Shang Wang, Longqiu Li, Yanhong Tian, Andreu Cabot, Qing Sun   +8 more
wiley   +1 more source

Co-embedding of edges and nodes with deep graph convolutional neural networks

Scientific Reports, 2023
Graph neural networks (GNNs) have significant advantages in dealing with non-Euclidean data and have been widely used in various fields. However, most of the existing GNN models face two main challenges: (1) Most GNN models built upon the message-passing
Yuchen Zhou, Hongtao Huo, Zhiwen Hou, Lingbin Bu, Jingyi Mao, Yifan Wang, Xiaojun Lv, Fanliang Bu   +7 more
doaj   +1 more source

End‐to‐End Sensing Systems for Breast Cancer: From Wearables for Early Detection to Lab‐Based Diagnosis Chips

Advanced Materials Technologies, EarlyView.
This review explores advances in wearable and lab‐on‐chip technologies for breast cancer detection. Covering tactile, thermal, ultrasound, microwave, electrical impedance tomography, electrochemical, microelectromechanical, and optical systems, it highlights innovations in flexible electronics, nanomaterials, and machine learning.
Neshika Wijewardhane, Lyn I. Jones, Richard M. Martin, Helen Winter, Faezeh Arab Hassani   +4 more
wiley   +1 more source

A review on the applications of graph neural networks in materials science at the atomic scale

Materials Genome Engineering Advances
In recent years, interdisciplinary research has become increasingly popular within the scientific community. The fields of materials science and chemistry have also gradually begun to apply the machine learning technology developed by scientists from ...
Xingyue Shi, Linming Zhou, Yuhui Huang, Yongjun Wu, Zijian Hong   +4 more
doaj   +1 more source

Transducers Across Scales and Frequencies: A System‐Level Framework for Multiphysics Integration and Co‐Design

Advanced Materials Technologies, EarlyView.
Transducers convert physical signals into electrical and optical representations, yet each mechanism is bounded by intrinsic trade‐offs across bandwidth, sensitivity, speed, and energy. This review maps transduction mechanisms across physical scale and frequency, showing how heterogeneous integration and multiphysics co‐design transform isolated ...
Aolei Xu, Mengyao Xiao, Zhouli Sui, Yinpeng Wang, Daoye Zheng, Yuxin Liu, Luwei Wang, Huajun Liu, Chengkuo Lee   +8 more
wiley   +1 more source

A Network Scanning Organization Discovery Method Based on Graph Convolutional Neural Network

Information
With the quick development of network technology, the number of active IoT devices is growing rapidly. Numerous network scanning organizations have emerged to scan and detect network assets around the clock.
Pengfei Xue, Luhan Dong, Chenyang Wang, Cheng Huang, Jie Wang   +4 more
doaj   +1 more source

Graph Classification with 2D Convolutional Neural Networks [PDF]

, 2019
Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alternative, but processing graphs with CNNs is not trivial. To address this challenge, many sophisticated extensions of CNNs have recently been introduced.
Antoine J.-P. Tixier, Giannis Nikolentzos, Polykarpos Meladianos, Michalis Vazirgiannis   +3 more
openaire   +2 more sources

Processing of Incomplete Images by (Graph) Convolutional Neural Networks [PDF]

, 2020
We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) -- a type of graph convolutional networks ...
Tomasz Danel, Marek Smieja, Lukasz Struski, Przemyslaw Spurek, Lukasz Maziarka   +4 more
openaire   +3 more sources