Results 51 to 60 of about 39,156 (266)

Linear Graph Convolutional Networks. [PDF]

, 2020
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing a linear graph convolution operator. Despite its simplicity,
Navarin N., Erb W., Pasa L., Sperduti A.
openaire   +1 more source

Leak Detection in Water Supply Network Using a Data-Driven Improved Graph Convolutional Network

IEEE Access, 2023
Due to the complex correlation within data collection, it is a challenging task to detect leakage in the water supply network. The Graph Convolutional Network (GCN) has recently gained significant attention in correlation research. However, most existing
Suisheng Chen, Yun Wang, Wei Zhang, Hairong Zhang, Yuchen He   +4 more
doaj   +1 more source

Optoelectronic Nanofluidic Neural Networks for Ionic Computing

Advanced Materials, EarlyView.
An ion‐based optoelectronic nanofluidic memristor enables neuromorphic computing in aqueous environments. With tunable ionic memory and multimodal synaptic plasticity, it realizes densely connected ionic neural networks capable of image classification, motion prediction, logic computation, and real‐time in‐sensor computing, advancing fully connected ...
Yaxin Huang, Zhiyuan Du, Changjin Wu, Binglin Zeng, Yingnan Cao, Mingliang Li, Liren Zhang, Qingxin Guo, Chao Huang, Can Li, Jinyao Tang   +10 more
wiley   +1 more source

Graph convolutional networks for graphs containing missing features

Future Generation Computer Systems, 2021
Graph Convolutional Network (GCN) has experienced great success in graph analysis tasks. It works by smoothing the node features across the graph. The current GCN models overwhelmingly assume that the node feature information is complete. However, real-world graph data are often incomplete and containing missing features.
Hibiki Taguchi, Xin Liu 0020, Tsuyoshi Murata   +2 more
openaire   +2 more sources

A Modulation Classification Algorithm Based on Feature-Embedding Graph Convolutional Network

IEEE Access
Deep-learning is widely used in modulation classification to reduce labor and improve the efficiency. Graph convolutional network (GCN) is a type of feature extraction network for graph data.
Huali Zhu, Hua Xu, Yunhao Shi, Yue Zhang, Lei Jiang   +4 more
doaj   +1 more source

At Home Detection of Ovarian Health Biomarker in Menstruation Blood

Advanced Materials Technologies, EarlyView.
A lateral flow assay enables the detection of anti‐Müllerian hormone directly in unprocessed menstrual blood using silica‐gold nanoshells and smartphone‐assisted machine learning analysis. The platform supports decentralized, user‐operated testing in wearable and dipstick formats, highlighting the potential of menstrual blood as a non‐invasive matrix ...
Lucas Dosnon, Thomas Rduch, Salma Sherif Azer, Inge K. Herrmann   +3 more
wiley   +1 more source

TOWARDS A SPECTRUM OF GRAPH CONVOLUTIONAL NETWORKS [PDF]

2018 IEEE Data Science Workshop (DSW), 2018
We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies. Based on an analysis of GCNs with the help of the corresponding computation graphs, we propose a generalization of existing GCNs where
Mathias Niepert, Alberto García-Durán
openaire   +2 more sources

Relational graph convolutional networks: a closer look

PeerJ Computer Science, 2022
In this article, we describe a reproduction of the Relational Graph Convolutional Network (RGCN). Using our reproduction, we explain the intuition behind the model. Our reproduction results empirically validate the correctness of our implementations using benchmark Knowledge Graph datasets on node classification and link prediction
Thiviyan Thanapalasingam, Lucas van Berkel, Peter Bloem, Paul Groth   +3 more
openaire   +7 more sources

In Situ Integrated Titanium Oxide Synaptic Phototransistor Enabling Multimodal Plasticity and Noise‐Robust Selective Attention

Advanced Materials Technologies, EarlyView.
An in situ integrated TiO2/SiOx/Al2O3 synaptic phototransistor couples ultraviolet and electrical stimuli within a scalable, CMOS‐compatible oxide stack. Multimodal plasticity, spike‐timing‐dependent learning, and bee‐inspired associative conditioning are achieved through trap‐mediated temporal dynamics.
Youngbin Yoon, Jaehee Lee, Jeongwook Kwon, Yongki Kim, Myunghun Shin, Jung Wook Lim   +5 more
wiley   +1 more source

Smart Contract Bytecode Vulnerability Detection Method Based on Heterogeneous Graphs and Instruction Sequences [PDF]

Jisuanji kexue
In recent years,the security issues of smart contracts have become increasingly prominent,and vulnerability detection has become a key challenge.In scenarios where source code is not publicly available,bytecode-based detection methods have attracted ...
SONG Jianhua, CAO Kai, ZHANG Yan
doaj   +1 more source