A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
DeepGCNs: Can GCNs Go as Deep as CNNs?
[article]
2019
arXiv
pre-print
Preserved Fulltext
Other Versions
We believe that the community can greatly benefit from this work, as it opens up many opportunities for advancing GCN-based research. ...
In this work, we present new ways to successfully train very deep GCNs. ...
Extensive experiments show that by adding skip connections to GCNs, we can alleviate the difficulty of training, which is the primary problem impeding GCNs to go deeper. ...
arXiv:1904.03751v2
fatcat:kkcxgwcchvb3nc7mxfdvrhaoyy
DeepGCNs: Making GCNs Go as Deep as CNNs
[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.
Other Versions
This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. ...
We show the benefit of using deep GCNs (with as many as 112 layers) experimentally across various datasets and tasks. ...
from CNNs (i.e. residual/dense connections and dilated convolutions) can be transferred to GCNs in order to make GCNs go as deep as CNNs. ...
arXiv:1910.06849v2
fatcat:4rjqgbw3y5ae7hhthuxnwjjodi
Enabling "Untact" Culture via Online Product Recommendations: An Optimized Graph-CNN based Approach
2020
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 2020; you can also visit the original URL.
The file type is application/pdf.
GCN uses the session graphs as input. ...
The experiments on data show that the optimized GCN (OpGCN) was able to achieve higher prediction rate with around 93% accuracy as compared with simple GCN (around 88%). ...
User can click on any item and just visit it e.g., just go through the description, or he can purchase that item. ...
doi:10.3390/app10165445
fatcat:lhcsxbg4szdgnjwolqbswgsjeq
Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
[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 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2003.05425v1 fatcat:iobedhs3cjak5gd736vfsqtbsyOther Versions
We propose Gauge Equivariant Mesh CNNs which generalize GCNs to apply anisotropic gauge equivariant kernels. ...
A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). ...
The empirical success of CNNs on such spaces has generated interest to generalize convolutions to more general spaces like graphs or Riemannian manifolds, creating a field now known as geometric deep learning ...
arXiv:2003.05425v3
fatcat:jv4txtctfrgmvjpkguvmttu4r4
3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs
[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.
By iteratively and hierarchically fusing the features across different layers and stages of the CNNs and GCNs, our approach can provide a dense face alignment and 3D face reconstruction simultaneously ...
This is achieved by seamlessly combining standard convolutional neural networks (CNNs) with Graph Convolution Networks (GCNs). ...
It has been shown that as layers go deeper, DenseGCN can prevent vanishing gradient problems. ...
arXiv:2203.04643v1
fatcat:toyy4fcrrrg73batvoparlad7u
CNN LEGO: Disassembling and Assembling Convolutional Neural Network
[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.
Inspired by the above visual perception mechanism, we investigate a new task, termed as Model Disassembling and Assembling (MDA-Task), which can disassemble the deep models into independent parts and assemble ...
Extensive experiments demonstrate that the assembled CNN classifier can achieve close accuracy with the original classifier without any fine-tune, and excess original performance with one-epoch fine-tune ...
The MDA-Task is supposed to be appropriate for existing deep learning model such as CNN, GCN, GNN, RNN, Transformer, and et al. ...
arXiv:2203.13453v1
fatcat:l7wavam4rfbdtccl5m5hcha7dm
CNN-based Dual-Chain Models for Knowledge Graph Learning
[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
In this paper, we present a new convolutional neural network (CNN)-based dual-chain model. ...
Different from translation based methods, in our model, interactions among relations and entities are directly captured via CNN over their embeddings. ...
In this paper, we present our efforts toward improving knowledge graph learning as follows: • We present new deep learning methods, termed as Convolutional Neural Network (CNN)-based Dual-Chain methods ...
arXiv:1911.06910v2
fatcat:32amgvm7svhbborva6vfhx5byq
Cross-Modal Feature Representation Learning and Label Graph Mining in a Residual Multi-Attentional CNN-LSTM Network for Multi-Label Aerial Scene Classification
2022
Remote Sensing
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.
Moreover, semantic labels are embedded by language model and then form a label graph which can be further mapped by advanced graph convolutional networks (GCN). ...
Even worse, the preparation of a labeled dataset for the training of deep networks is more difficult due to multiple labels. ...
Similarly, deep learning can also be utilized in many remote sensing tasks such as segmentation [36] and detection [7] , so as to perceive different targets in remote sensing graphics. ...
doi:10.3390/rs14102424
fatcat:nfkrcuquhrabxfclnvjbz4ae6u
Two Ensemble-CNN Approaches for Colorectal Cancer Tissue Type Classification
2021
Journal of Imaging
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.
For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). ...
For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. ...
In more detail, intre-tumor heterogeneity can aid the understanding of TME's effect on patient prognosis, as well as identify novel aggressive phenotypes that can be further investigated as potential targets ...
doi:10.3390/jimaging7030051
pmid:34460707
fatcat:efdcjawdczhprcwmdf2jcrg6ye
A pixel cluster CNN and spectral-spatial fusion algorithm for hyperspectral image classification with small-size training samples
2021
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
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.
Convolutional neural networks (CNNs) can automatically learn features from the hyperspectral image (HSI) data, avoiding the difficulty of manually extracting features. ...
Experiments based on three standard HSIs demonstrate that the proposed algorithm can get better performance than the conventional CNN and also outperforms other studied algorithms in the case of small ...
GCN-CNN respectively. ...
doi:10.1109/jstars.2021.3068864
fatcat:zmxodwerbfcblp2ktuamjvdk5a
CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope
2021
Electronics
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.
Furthermore, achieving innovations in architecture results in a tremendous enhancement in the capacity of the deep CNN. ...
This survey paper focuses mainly on the primary taxonomy and newly released deep CNN architectures, and it divides numerous recent developments in CNN architectures into eight groups. ...
GCN: Graph Convolutional Network (2016) Graphs can be found in a variety of application disciplines, including as bioinformatics, social analysis, and computer vision. ...
doi:10.3390/electronics10202470
fatcat:aqhrysjtbjagzl6byalgy2du5a
DeepGOA: Predicting Gene Ontology Annotations of Proteins via Graph Convolutional Network
2019
2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
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.
The ablation study proves that GCN can employ the knowledge of GO and boost the performance. ...
To use the knowledge encoded in the GO hierarchy, we propose a deep Graph Convolutional Network (GCN) based model (DeepGOA) to predict GO annotations of proteins. ...
We can learn the information on the GO DAG by stacking the GCN layers. ...
doi:10.1109/bibm47256.2019.8983075
dblp:conf/bibm/ZhouWZY19
fatcat:yo5lt64m3vhjbgko2jfpq7hgdq
Multi-Graph Convolutional Network for Short-Term Passenger Flow Forecasting in Urban Rail Transit
[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.
Other Versions
In this study, we propose a deep-learning architecture called Conv-GCN combining graph convolutional network (GCN) and 3D convolutional neural network (3D CNN). ...
Multi-graph GCN network can capture spatiotemporal correlations and topological information in a whole network. Then, a 3D CNN is applied to deeply integrate the inflow and outflow information. ...
The GCN-based models, however, generally use one to four GCN layers. They cannot go as deep as CNN-based models [21] . Therefore, some deep spatial correlations cannot be effectively captured. ...
arXiv:2001.07512v2
fatcat:2gi7qcasfndxfb2fnrabnzq3zu
Predicting functions of maize proteins using graph convolutional network
2020
BMC Bioinformatics
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.
To use the knowledge encoded in the GO hierarchy, we propose a deep Graph Convolutional Network (GCN) based model (DeepGOA) to predict GO annotations of proteins. ...
The ablation study proves that GCN can employ the knowledge of GO and boost the performance. Codes and datasets are available at http://mlda.swu.edu.cn/codes.php?name=DeepGOA . ...
We can learn the deep information of GO terms on the GO DAG by stacking the GCN layers. ...
doi:10.1186/s12859-020-03745-6
pmid:33323113
fatcat:sueaa46xlrbq7f7u3earyre5km
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional 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.
Other Versions
representation, as GCN is more suitable for constructing deeper network than spectral graph convolution-based approaches. ...
Quantitative validations over invariance of the representations also demonstrate strong invariance of deep representations of SWN-GCN over rotations. ...
Conclusion We proposed a network that yields equivariant representation with SWN-GCN and invariant representation using GAP. ...
arXiv:2106.09996v2
fatcat:m7lv43z3urgspe2cvi7agta66y
« Previous
Showing results 1 — 15 out of 1,475 results