A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Adaptive Propagation Graph Convolutional Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Graph convolutional networks (GCNs) are a family of neural network models that perform inference on graph data by interleaving vertex-wise operations and message-passing exchanges across nodes. ...
We show that the proposed adaptive propagation GCN (AP-GCN) achieves superior or similar results to the best proposed models so far on a number of benchmarks, while requiring a small overhead in terms ...
GRAPH CONVOLUTIONAL NEURAL NETWORKS A. ...
arXiv:2002.10306v2
fatcat:spkggj2ki5bl5ovrzzl2mqf6j4
Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Based on this observation, we then propose a unified adaptive neighborhood feature propagation model and derive a novel Adaptive Neighborhood Graph Propagation Network (ANGPN) for data representation and ...
Graph Convolutional Networks (GCNs) have been widely studied for compact data representation and semi-supervised learning tasks. ...
They also [13] propose Graph mask Convolutional Network (GmCN) by selecting neighbors adaptively in GCN operation. ...
arXiv:1908.05153v2
fatcat:ljoufrnoundfhktnjjk54hc77e
Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Graph Convolutional Networks (GCNs) have been widely applied in various fields due to their significant power on processing graph-structured data. ...
To adaptively learn the propagation process, we introduce two measurements of homophily degree between node pairs, which is learned based on topological and attribute information, respectively. ...
To solve this problem, we focus on designing an adaptive propagation mechanism for both heterophilic and homophilic networks, and giving a new HOmophily-Guided Graph Convolutional Network called HOG-GCN ...
arXiv:2112.13562v1
fatcat:jwi4mrv4t5hjll5die46e4duzy
Topology and Prediction Focused Research on Graph Convolutional Neural Networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
A brief discussion of Topology Adaptive Graph Convolutional Networks (TAGCN) is presented as an approach motivated by DSPg and future research directions using this approach are briefly discussed. ...
Recently, research on graph convolutional neural networks (GCNN) has increased dramatically as researchers try to replicate the success of CNN for graph structured data. ...
[8] in their adaptation of common image identification convolutional network topologies to include graph convolutions. ...
arXiv:1808.07769v1
fatcat:tgjs62zqonb2ni6rjwiq3uv3ny
Deep learning long-range information in undirected graphs with wave networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We compare wave to graph convolution, an architecture based on local aggregation, and find that wave learns three different graph-based tasks with greater efficiency and accuracy. ...
Graph algorithms are key tools in many fields of science and technology. Some of these algorithms depend on propagating information between distant nodes in a graph. ...
Recently, deep learning architectures, usually variants of convolutional neural networks, have been adapted for graph data [9, 22] . ...
arXiv:1810.12153v1
fatcat:yls72fvqqvefdjsctqf7zyuohy
STAGCN: Spatial–Temporal Attention Graph Convolution Network for Traffic Forecasting
2022
Mathematics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The static graph aims to model global space adaptability, and the dynamic graph is designed to capture local dynamics in the traffic network. ...
In this paper, we propose a spatial–temporal attention graph convolution network (STAGCN), which acquires a static graph and a dynamic graph from data without any prior knowledge. ...
On the other hand, a shallow graph convolution network cannot sufficiently propagate the edge node information to the entire graph. ...
doi:10.3390/math10091599
fatcat:5pkibiw3c5f6xmnr3azcotgmim
GeniePath: Graph Neural Networks with Adaptive Receptive Paths
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. ...
Our method works in both transductive and inductive settings, and extensive experiments compared with competitive methods show that our approaches yield state-of-the-art results on large graphs. ...
Graph Convolutional Networks Generalizing convolutions to graphs aims to encode the nodes with signals lie in the receptive fields. ...
arXiv:1802.00910v3
fatcat:a7eqmroa6zatdco2p6xek2hp3u
Adaptive Context-Aware Multi-Modal Network for Depth Completion
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Since the graph structure varies from sample to sample, we then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. ...
To address this issue, we propose to adopt the graph propagation to capture the observed spatial contexts. Specifically, we first construct multiple graphs at different scales from observed pixels. ...
Our extensive experiments have demonstrated the effectiveness of the network as well as the network components. Figure 2 : 2 Illustration of convolution and graph propagation. ...
arXiv:2008.10833v1
fatcat:qp6vwjryqvaxti37twj6w3pjgy
GeniePath: Graph Neural Networks with Adaptive Receptive Paths
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. ...
Our method works in both transductive and inductive settings, and extensive experiments compared with competitive methods show that our approaches yield state-of-the-art results on large graphs. ...
Graph Convolutional Networks Generalizing convolutions to graphs aims to encode the nodes with signals lie in the receptive fields. ...
doi:10.1609/aaai.v33i01.33014424
fatcat:wovxjpkezbfxzarmccbcbp5a2u
GmCN: Graph Mask Convolutional Network
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Graph Convolutional Networks (GCNs) have shown very powerful for graph data representation and learning tasks. ...
To address these issues, we propose a novel Graph mask Convolutional Network (GmCN) in which nodes can adaptively select the optimal neighbors in their feature aggregation to better serve GCN learning. ...
Conclusion This paper proposes a novel Graph mask Convolutional Network (GmCN) for graph data representation and semi-supervised learning. ...
arXiv:1910.01735v2
fatcat:mzgmlpc5nrccbgqbmxktnecw7i
Adaptive Interaction Modeling via Graph Operations Search
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling ...
To this end, we first design the search space with several basic graph operations that explicitly capture different relations in videos. ...
Feature Aggregation Graph convolution network (GCN) [17] is commonly used to model relations. ...
doi:10.1109/cvpr42600.2020.00060
dblp:conf/cvpr/LiZT0L20
fatcat:kwy7unskm5hmlogfh7pm5ae4rm
Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction
2022
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
graph convolution to capture the dynamic inter-node dependency adaptively at different time slots. ...
While various graph-based spatiotemporal networks have been proposed for traffic prediction, most of them rely on predefined graphs from different views or static adaptive matrices. ...
and incorporates an adaptive adjacency graph in the graph convolution module. • MTGNN [21] : This model introduces a uni-directional adaptive graph and mix-hop propagation into graph convolutions, and ...
doi:10.3390/app12062842
fatcat:jt5b6gtiv5fo3mt7zcpsafxwny
Graph Highway Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. ...
However, they suffer from the notorious over-smoothing problem, in which the learned representations of densely connected nodes converge to alike vectors when many (>3) graph convolutional layers are stacked ...
Graph Convolutional Networks
Recap GCN were proposed by for semisupervised node classification. ...
arXiv:2004.04635v1
fatcat:sjr4zqdikjaercrm3manlh2djm
Propagation with Adaptive Mask then Training for Node Classification on Attributed Networks
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
By decoupling two critical operations in Graph Convolutional Networks (GCNs), namely feature transformation and neighborhood aggregation, some recent works of decoupled GCNs could support the information ...
To address these issues, we propose a new method called the itshape Propagation with Adaptive Mask then Training (PAMT). ...
Among which, Graph Convolutional Network (GCN) based methods [5, 6, 7, 8] have gained great success with high performance. The core component of GCN-based models is the graph convolution layer. ...
arXiv:2206.10142v2
fatcat:lpjisyjedjflnjjpamxpllh5qq
Adaptive Kernel Graph Neural Network
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt. ...
The layer-wise graph convolution in GNNs is shown to be powerful at capturing graph topology. ...
AI magazine, 29(3): 93–93.
with graph convolutional networks via importance sampling. ...
arXiv:2112.04575v1
fatcat:xwid5yfndrcmtfcsd4psywabwm
« Previous
Showing results 1 — 15 out of 25,875 results