You are currently viewing a beta version of our website. If you spot anything unusual, kindly let us know.
Altmetrics
Downloads
133
Views
43
Comments
0
A peer-reviewed article of this preprint also exists.
This version is not peer-reviewed
CNN | Convolutional Neural Network |
GAN | Generative Adversarial Networks |
VAE | Variational Auto-Encoder |
GNN | Graph Neural Networks |
GCN | Graph Convolutional layers |
ELBO | Evidence Lower Bound |
GAE | Graph Auto-Encoders |
VGAE | Variational Graph Auto-Encoders |
ReNN-Pool | Recursive Nearest Neighbour Pooling |
Layers | Parameters | N nodes | N edges | |
---|---|---|---|---|
Graph Encoder | GraphConv(1, 16, ’mean’) | 48 | 21.952 | 128.576 |
ReNN-Pool | - | 10.976 | 93.960 | |
GraphConv(16, 32, ’mean’) | 1.056 | 10.976 | 93.960 | |
ReNN-Pool | - | 1.470 | 21.952 | |
GraphConv(32, 64, ’mean’) | 4.160 | 1.470 | 21.952 | |
ReNN-Pool | - | 236 | 6.206 | |
Linear(64 x 236, 64) | 966.720 | - | - | |
Linear(64, 2*) | 130 | - | - | |
Linear(64, 2*) | 130 | - | - | |
Graph Decoder | Linear(2*, 64) | 192 | - | - |
Linear(64, 64 x 236) | 981.760 | - | - | |
ReNN-Unpool | - | 1.470 | 21.952 | |
GraphConv(64, 32, ’mean’) | 4.128 | 1.470 | 21.952 | |
ReNN-Unpool | - | 10.976 | 93.960 | |
GraphConv(32, 16, ’mean’) | 1.040 | 10.976 | 93.960 | |
ReNN-Unpool | - | 21.952 | 128.576 | |
GraphConv(16, 1, ’mean’) | 33 | 21.952 | 128.576 |
Layers | Parameters | N nodes | N edges | |
---|---|---|---|---|
Graph Encoder | GraphConv(3, 16, ’mean’) | 112 | 4.096 | 16.128 |
ReNN-Pool | - | 2048 | 15.874 | |
Linear(1, 15.874) | 31.748 | - | - | |
GraphConv(16, 32, ’mean’, ) | 1.056 | 2048 | 15.874 | |
ReNN-Pool | - | 528 | 3.906 | |
Linear(1, 3.906) | 7,812 | - | - | |
GraphConv(32, 64, ’mean’, ) | 4.160 | 528 | 3.906 | |
ReNN-Pool | - | 136 | 930 | |
Linear(64 x 136, 64) | 557.120 | - | - | |
Linear(64, 5) | 325 | - | - | |
Linear(64, 5) | 325 | - | - | |
Graph Decoder | Linear(5, 64) | 384 | - | - |
Linear(64, 64 x 136) | 565.760 | - | - | |
ReNN-Unpool | - | 528 | 3.906 | |
Linear(1, 3.906) | 7,812 | - | - | |
GraphConv(64, 32, ’mean’, ) | 4.128 | 528 | 3.906 | |
ReNN-Unpool | - | 2.048 | 15.874 | |
Linear(1, 15.874) | 31.748 | - | - | |
GraphConv(32, 16, ’mean’, ) | 1.040 | 2.048 | 15.874 | |
ReNN-Unpool | - | 4.096 | 16.128 | |
GraphConv(16, 3, ’mean’) | 99 | 4.096 | 16.128 |
1 | |
2 | |
3 |
Dataset | Z profile error | R profile error | Total energy error | |
---|---|---|---|---|
Water | 5.8 ± 3.4% | 2.6 ± 1.6% | 2.2 ± 1.6% | 99.3 ± 0.1% |
Water + Slice | 6.9 ± 3.4% | 3.0 ± 1.2% | 2.2 ± 1.6% | 98.6 ± 0.3% |
Pooling | Z profile error | R profile error | Total energy error | |
---|---|---|---|---|
ReNN-Pool | 6.9 ± 3.4% | 3.0 ± 1.2% | 2.2 ± 1.6% | 98.6 ± 0.3% |
Random Pool | 172.6 ± 21.7% | 52.2 ± 3.7% | 2.0 ± 1.5% | 92.4 ± 0.4% |
Top-k Pool | 51.7 ± 3.4% | 75.1 ± 9.1% | 4.0 ± 2.6% | 79.9 ± 1.3% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Submitted:
30 January 2023
Posted:
02 February 2023
You are already at the latest version
A peer-reviewed article of this preprint also exists.
This version is not peer-reviewed
Submitted:
30 January 2023
Posted:
02 February 2023
You are already at the latest version
CNN | Convolutional Neural Network |
GAN | Generative Adversarial Networks |
VAE | Variational Auto-Encoder |
GNN | Graph Neural Networks |
GCN | Graph Convolutional layers |
ELBO | Evidence Lower Bound |
GAE | Graph Auto-Encoders |
VGAE | Variational Graph Auto-Encoders |
ReNN-Pool | Recursive Nearest Neighbour Pooling |
Layers | Parameters | N nodes | N edges | |
---|---|---|---|---|
Graph Encoder | GraphConv(1, 16, ’mean’) | 48 | 21.952 | 128.576 |
ReNN-Pool | - | 10.976 | 93.960 | |
GraphConv(16, 32, ’mean’) | 1.056 | 10.976 | 93.960 | |
ReNN-Pool | - | 1.470 | 21.952 | |
GraphConv(32, 64, ’mean’) | 4.160 | 1.470 | 21.952 | |
ReNN-Pool | - | 236 | 6.206 | |
Linear(64 x 236, 64) | 966.720 | - | - | |
Linear(64, 2*) | 130 | - | - | |
Linear(64, 2*) | 130 | - | - | |
Graph Decoder | Linear(2*, 64) | 192 | - | - |
Linear(64, 64 x 236) | 981.760 | - | - | |
ReNN-Unpool | - | 1.470 | 21.952 | |
GraphConv(64, 32, ’mean’) | 4.128 | 1.470 | 21.952 | |
ReNN-Unpool | - | 10.976 | 93.960 | |
GraphConv(32, 16, ’mean’) | 1.040 | 10.976 | 93.960 | |
ReNN-Unpool | - | 21.952 | 128.576 | |
GraphConv(16, 1, ’mean’) | 33 | 21.952 | 128.576 |
Layers | Parameters | N nodes | N edges | |
---|---|---|---|---|
Graph Encoder | GraphConv(3, 16, ’mean’) | 112 | 4.096 | 16.128 |
ReNN-Pool | - | 2048 | 15.874 | |
Linear(1, 15.874) | 31.748 | - | - | |
GraphConv(16, 32, ’mean’, ) | 1.056 | 2048 | 15.874 | |
ReNN-Pool | - | 528 | 3.906 | |
Linear(1, 3.906) | 7,812 | - | - | |
GraphConv(32, 64, ’mean’, ) | 4.160 | 528 | 3.906 | |
ReNN-Pool | - | 136 | 930 | |
Linear(64 x 136, 64) | 557.120 | - | - | |
Linear(64, 5) | 325 | - | - | |
Linear(64, 5) | 325 | - | - | |
Graph Decoder | Linear(5, 64) | 384 | - | - |
Linear(64, 64 x 136) | 565.760 | - | - | |
ReNN-Unpool | - | 528 | 3.906 | |
Linear(1, 3.906) | 7,812 | - | - | |
GraphConv(64, 32, ’mean’, ) | 4.128 | 528 | 3.906 | |
ReNN-Unpool | - | 2.048 | 15.874 | |
Linear(1, 15.874) | 31.748 | - | - | |
GraphConv(32, 16, ’mean’, ) | 1.040 | 2.048 | 15.874 | |
ReNN-Unpool | - | 4.096 | 16.128 | |
GraphConv(16, 3, ’mean’) | 99 | 4.096 | 16.128 |
1 | |
2 | |
3 |
Dataset | Z profile error | R profile error | Total energy error | |
---|---|---|---|---|
Water | 5.8 ± 3.4% | 2.6 ± 1.6% | 2.2 ± 1.6% | 99.3 ± 0.1% |
Water + Slice | 6.9 ± 3.4% | 3.0 ± 1.2% | 2.2 ± 1.6% | 98.6 ± 0.3% |
Pooling | Z profile error | R profile error | Total energy error | |
---|---|---|---|---|
ReNN-Pool | 6.9 ± 3.4% | 3.0 ± 1.2% | 2.2 ± 1.6% | 98.6 ± 0.3% |
Random Pool | 172.6 ± 21.7% | 52.2 ± 3.7% | 2.0 ± 1.5% | 92.4 ± 0.4% |
Top-k Pool | 51.7 ± 3.4% | 75.1 ± 9.1% | 4.0 ± 2.6% | 79.9 ± 1.3% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Nikita Andriyanov
Mathematics,
2022
Lorenzo Arsini
et al.
Algorithms,
2023
Lili Sun
et al.
Future Internet,
2021
© 2024 MDPI (Basel, Switzerland) unless otherwise stated