Skip to content
Snippets Groups Projects
Commit 80dad811 authored by Erick Lavoie's avatar Erick Lavoie
Browse files

Added convergence speed comparison at 1000 nodes

parent d10d6c0e
No related branches found
No related tags found
No related merge requests found
figures/d-cliques-cifar10-1000-vs-1-node-test-accuracy.png

53.3 KiB

figures/d-cliques-cifar10-1000-vs-1-node-training-loss.png

102 KiB

figures/d-cliques-mnist-1000-nodes-comparison.png

109 KiB

......@@ -367,8 +367,16 @@ We solve this problem by decoupling the gradient averaging from the weight avera
% python ../../../learn-topology/tools/plot_convergence.py 1-node-iid/all/2021-03-10-09:20:03-CET fully-connected/all/2021-03-10-09:25:19-CET clique-ring/all/2021-03-10-18:14:35-CET fully-connected-cliques/all/2021-03-10-10:19:44-CET --add-min-max --yaxis test-accuracy --labels '1-node IID bsz=12800' '100-nodes non-IID fully-connected bsz=128' '100-nodes non-IID D-Cliques (Ring) bsz=128' '100-nodes non-IID D-Cliques (Fully-Connected) bsz=128' --legend 'lower right' --ymin 85 --ymax 92.5 --save-figure ../../figures/d-cliques-mnist-vs-1-node-test-accuracy.png
\centering
\includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-vs-1-node-test-accuracy}
\caption{\label{fig:d-cliques-mnist-linear-w-clique-averaging-w-initial-averaging} MNIST: D-Cliques Convergence Speed}
\caption{\label{fig:d-cliques-mnist-linear-w-clique-averaging-w-initial-averaging} MNIST: D-Cliques Convergence Speed (100 nodes)}
\end{figure}
% To regenerate the figure, from directory results/mnist
% python ../../../learn-topology/tools/plot_convergence.py 1-node-iid/all/2021-03-10-09:20:03-CET ../scaling/1000/mnist/fully-connected-cliques/all/2021-03-14-17:56:26-CET ../scaling/1000/mnist/smallworld-logn-cliques/all/2021-03-23-21:45:39-CET ../scaling/1000/mnist/fractal-cliques/all/2021-03-14-17:41:59-CET ../scaling/1000/mnist/clique-ring/all/2021-03-13-18:22:36-CET --add-min-max --yaxis test-accuracy --legend 'lower right' --ymin 84 --ymax 92.5 --labels '1 node IID' 'd-cliques (fully-connected cliques)' 'd-cliques (smallworld)' 'd-cliques (fractal)' 'd-cliques (ring)' --save-figure ../../figures/d-cliques-mnist-1000-nodes-comparison.png
\begin{figure}[htbp]
\centering
\includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-1000-nodes-comparison}
\caption{\label{fig:d-cliques-mnist-1000-nodes-comparison} MNIST: D-Clique Convergence Speed (1000 nodes)}
\end{figure}
\begin{figure}[htbp]
\centering
......@@ -527,7 +535,28 @@ In addition, it is important that all nodes are initialized with the same model
\includegraphics[width=\textwidth]{figures/d-cliques-cifar10-vs-1-node-test-accuracy}
\caption{\label{fig:d-cliques-cifar10-test-accuracy} Test Accuracy}
\end{subfigure}
\caption{\label{fig:d-cliques-cifar10-convolutional} D-Cliques with Convolutional Network on CIFAR10.}
\caption{\label{fig:d-cliques-cifar10-convolutional} D-Cliques Convergence Speed with Convolutional Network on CIFAR10 (100 nodes).}
\end{figure}
\begin{figure}[htbp]
\centering
% To regenerate the figure, from directory results/cifar10
% python ../../../learn-topology/tools/plot_convergence.py 1-node-iid/all/2021-03-10-13:52:58-CET ../scaling/1000/cifar10/fully-connected-cliques/all/2021-03-14-17:41:20-CET ../scaling/1000/cifar10/fractal-cliques/all/2021-03-14-17:42:46-CET ../scaling/1000/cifar10/clique-ring/all/2021-03-14-09:55:24-CET --add-min-max --yaxis training-loss --labels '1-node IID' 'd-cliques (fully-connected cliques)' 'd-cliques (fractal)' 'd-cliques (ring)' --legend 'upper right' --ymax 3 --save-figure ../../figures/d-cliques-cifar10-1000-vs-1-node-training-loss.png
\begin{subfigure}[b]{0.48\textwidth}
\centering
\includegraphics[width=\textwidth]{figures/d-cliques-cifar10-1000-vs-1-node-training-loss}
\caption{\label{fig:d-cliques-cifar10-1000-vs-1-node-training-loss} Training Loss}
\end{subfigure}
\hfill
% To regenerate the figure, from directory results/cifar10
% python ../../../learn-topology/tools/plot_convergence.py 1-node-iid/all/2021-03-10-13:52:58-CET ../scaling/1000/cifar10/fully-connected-cliques/all/2021-03-14-17:41:20-CET ../scaling/1000/cifar10/fractal-cliques/all/2021-03-14-17:42:46-CET ../scaling/1000/cifar10/clique-ring/all/2021-03-14-09:55:24-CET --add-min-max --yaxis test-accuracy --labels '1-node IID' 'd-cliques (fully-connected cliques)' 'd-cliques (fractal)' 'd-cliques (ring)' --legend 'lower right' --save-figure ../../figures/d-cliques-cifar10-1000-vs-1-node-test-accuracy.png
\begin{subfigure}[b]{0.48\textwidth}
\centering
\includegraphics[width=\textwidth]{figures/d-cliques-cifar10-1000-vs-1-node-test-accuracy}
\caption{\label{fig:d-cliques-cifar10-1000-vs-1-node-test-accuracy} Test Accuracy}
\end{subfigure}
\caption{\label{fig:d-cliques-cifar10-convolutional} D-Cliques Convergence Speed with Convolutional Network on CIFAR10 (1000 nodes).}
\end{figure}
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment