Results 41 to 50 of about 36,148 (258)

Exploiting Weak Ties in Incomplete Network Datasets Using Simplified Graph Convolutional Neural Networks

Machine Learning and Knowledge Extraction, 2020
This paper explores the value of weak-ties in classifying academic literature with the use of graph convolutional neural networks. Our experiments look at the results of treating weak-ties as if they were strong-ties to determine if that assumption ...
Neda H. Bidoki, Alexander V. Mantzaris, Gita Sukthankar   +2 more
doaj   +1 more source

Graph learning-based spatial-temporal graph convolutional neural networks for traffic forecasting

Connection Science, 2022
Traffic forecasting is highly challenging due to its complex spatial and temporal dependencies in the traffic network. Graph Convolutional Neural Network (GCN) has been effectively used for traffic forecasting due to its excellent performance in ...
Na Hu, Dafang Zhang, Kun Xie, Wei Liang, Meng-Yen Hsieh   +4 more
doaj   +1 more source

Adaptive Graph Convolutional Neural Networks

Proceedings of the AAAI Conference on Artificial Intelligence, 2018
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity.
Ruoyu Li 0002, Sheng Wang 0001, Feiyun Zhu, Junzhou Huang   +3 more
openaire   +2 more sources

MIMO Graph Filters for Convolutional Neural Networks [PDF]

2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2018
Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNNs) for a wide array of inference and reconstruction tasks. CNNs implement three basic blocks: convolution, pooling and pointwise nonlinearity.
Fernando Gama, Antonio G. Marques, Alejandro Ribeiro, Geert Leus   +3 more
openaire   +3 more sources

Convolution Based Graph Representation Learning from the Perspective of High Order Node Similarities

Mathematics, 2022
Nowadays, graph representation learning methods, in particular graph neural network methods, have attracted great attention and performed well in many downstream tasks. However, most graph neural network methods have a single perspective since they start
Xing Li, Qingsong Li, Wei Wei, Zhiming Zheng   +3 more
doaj   +1 more source

Fast Graph Convolutional Recurrent Neural Networks [PDF]

2019 53rd Asilomar Conference on Signals, Systems, and Computers, 2019
This paper proposes a Fast Graph Convolutional Neural Network (FGRNN) architecture to predict sequences with an underlying graph structure. The proposed architecture addresses the limitations of the standard recurrent neural network (RNN), namely, vanishing and exploding gradients, causing numerical instabilities during training.
Sai Kiran Kadambari, Sundeep Prabhakar Chepuri   +1 more
openaire   +2 more sources

Dual-channel deep graph convolutional neural networks

Frontiers in Artificial Intelligence
The dual-channel graph convolutional neural networks based on hybrid features jointly model the different features of networks, so that the features can learn each other and improve the performance of various subsequent machine learning tasks.
Zhonglin Ye, Zhonglin Ye, Zhonglin Ye, Zhonglin Ye, Zhuoran Li, Zhuoran Li, Zhuoran Li, Zhuoran Li, Gege Li, Gege Li, Gege Li, Gege Li, Haixing Zhao, Haixing Zhao, Haixing Zhao, Haixing Zhao   +15 more
doaj   +1 more source

Non-convolutional graph neural networks.

Advances in Neural Information Processing Systems 37
Rethink convolution-based graph neural networks (GNN) -- they characteristically suffer from limited expressiveness, over-smoothing, and over-squashing, and require specialized sparse kernels for efficient computation. Here, we design a simple graph learning module entirely free of convolution operators, coined random walk with unifying memory (RUM ...
Yuanqing Wang, Kyunghyun Cho
openaire   +3 more sources

Image Denoising with Graph-Convolutional Neural Networks [PDF]

2019 IEEE International Conference on Image Processing (ICIP), 2019
IEEE International Conference on Image Processing (ICIP ...
Valsesia D., Fracastoro G., Magli E.
openaire   +2 more sources

Oxidized MoS2‐Based Multifunctional Memristive Hardware for Energy‐Efficient mmWave Signal Processing and In‐Memory Matrix Multiplication

Advanced Functional Materials, EarlyView.
Thermally oxidized MoS2‐based radio‐frequency switches enable a multifunctional platform that unifies broadband RF switching and in‐memory computation. The device achieves a cutoff frequency of 33.2 THz with high energy efficiency and supports hardware‐aware signal processing.
Juho Son, Changwoo Pyo, Sungmoon Park, Yoongi Cho, Seungchan Lee, Myungsoo Kim   +5 more
wiley   +1 more source