Added CIFAR10 scaling figures

main.tex

@@ -301,8 +301,7 @@ We solve this problem by decoupling the gradient averaging from the weight avera
 \caption{\label{fig:d-cliques-mnist-clique-clustering} MNIST: Effects of Clustering within Cliques on Convergence Speed.}
 \end{figure}
 
-     \begin{figure}[htbp]
-         \centering
+% REMOVED: Constant Batch-size
 %         % To regenerate the figure, from directory results/scaling
 %% python ../../../learn-topology/tools/plot_convergence.py 10/mnist/fully-connected-cliques/all/2021-03-10-14:40:35-CET ../mnist/fully-connected-cliques/all/2021-03-10-10:19:44-CET 1000/mnist/fully-connected-cliques/all/2021-03-10-16:44:35-CET --labels '10 nodes bsz=128' '100 nodes bsz=128' '1000 nodes bsz=128 (45)' --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png --ymin 80 --add-min-max
 %         \begin{subfigure}[b]{0.48\textwidth}
@@ -310,14 +309,16 @@ We solve this problem by decoupling the gradient averaging from the weight avera
 %         \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fully-connected-cst-bsz}
 %         \caption{FCC: Constant Batch-Size}
 %     \end{subfigure}
-     
+
+     \begin{figure}[htbp]
+         \centering     
               % To regenerate the figure, from directory results/scaling
 % python ../../../learn-topology/tools/plot_convergence.py 10/mnist/fully-connected-cliques/all/2021-03-12-09:13:27-CET ../mnist/fully-connected-cliques/all/2021-03-10-10:19:44-CET 1000/mnist/fully-connected-cliques/all/2021-03-14-17:56:26-CET --labels '10 nodes bsz=1280' '100 nodes bsz=128' '1000 nodes bsz=13' --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png --ymin 80 --add-min-max
 
       \begin{subfigure}[b]{0.7\textwidth}
          \centering
          \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fully-connected-cst-updates}
-         \caption{Fully-Connected}
+         \caption{Fully-Connected (Cliques), $O(\frac{n^2}{c^2} + nc)$ edges}
      \end{subfigure}
      
           % To regenerate the figure, from directory results/scaling
@@ -325,7 +326,7 @@ We solve this problem by decoupling the gradient averaging from the weight avera
          \begin{subfigure}[b]{0.7\textwidth}
          \centering
          \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fractal-cliques-cst-updates}
-         \caption{Fractal}
+         \caption{Fractal, $O(nc)$ edges}
      \end{subfigure}  
 
      
@@ -334,10 +335,10 @@ We solve this problem by decoupling the gradient averaging from the weight avera
          \begin{subfigure}[b]{0.7\textwidth}
          \centering
          \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-clique-ring-cst-updates}
-         \caption{Ring}
+         \caption{Ring, $O(n)$ edges}
      \end{subfigure}  
      
-     \caption{\label{fig:d-cliques-mnist-scaling-fully-connected} MNIST: D-Clique Scaling Behaviour (Constant Updates per Epoch)}
+     \caption{\label{fig:d-cliques-mnist-scaling-fully-connected} MNIST: D-Clique Scaling Behaviour, where $n$ is the number of nodes, and $c$ the size of a clique (Constant Updates per Epoch).}
      \end{figure}
      
 Show scaling effect for 10, 100, 1000 nodes (with decreasing sample sizes) for Clique Ring, Fractal, Fully-Connected.
@@ -418,13 +419,40 @@ In addition, it is important that all nodes are initialized with the same model
 \caption{\label{fig:d-cliques-cifar10-clique-clustering} CIFAR10: Effects of Clustering within Cliques on Convergence Speed.}
 \end{figure}
 
-     \begin{figure}[htbp]
+
+     
+          \begin{figure}[htbp]
+         \centering
+     
               % To regenerate the figure, from directory results/scaling
-% python ../../../learn-topology/tools/plot_convergence.py 10/cifar10/fully-connected-cliques/all/2021-03-12-09:13:27-CET ../cifar10/fully-connected-cliques/all/2021-03-10-10:19:44-CET 1000/cifar10/fully-connected-cliques/all/2021-03-12-09:13:28-CET --labels '10 nodes bsz=1280' '100 nodes bsz=128' '1000 nodes bsz=13' --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-cifar10-scaling-fully-connected-cst-updates.png --ymin 80 --add-min-max
+% python ../../../learn-topology/tools/plot_convergence.py 10/cifar10/fully-connected-cliques/all/2021-03-13-19:06:02-CET ../cifar10/fully-connected-cliques/all/2021-03-10-13:58:57-CET 1000/cifar10/fully-connected-cliques/all/2021-03-14-17:41:20-CET --labels '10 nodes bsz=200' '100 nodes bsz=20' '1000 nodes bsz=2' --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-cifar10-scaling-fully-connected-cst-updates.png --add-min-max
+
+      \begin{subfigure}[b]{0.7\textwidth}
+         \centering
+         \includegraphics[width=\textwidth]{figures/d-cliques-cifar10-scaling-fully-connected-cst-updates}
+         \caption{Fully-Connected (Cliques), $O(\frac{n^2}{c^2} + nc)$ edges}
+     \end{subfigure}
+     
+          % To regenerate the figure, from directory results/scaling
+% python ../../../learn-topology/tools/plot_convergence.py 10/cifar10/fully-connected-cliques/all/2021-03-13-19:06:02-CET ../cifar10/fully-connected-cliques/all/2021-03-10-13:58:57-CET 1000/cifar10/fractal-cliques/all/2021-03-14-17:42:46-CET  --labels '10 nodes bsz=200' '100 nodes bsz=20' '1000 nodes bsz=2' --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-cifar10-scaling-fractal-cliques-cst-updates.png --add-min-max
+         \begin{subfigure}[b]{0.7\textwidth}
          \centering
-         %\includegraphics[width=\textwidth]{figures/d-cliques-cifar10-scaling-fully-connected-cst-updates}
-     \caption{\label{fig:d-cliques-cifar10-scaling-fully-connected} CIFAR10: Scaling Behaviour of Fully-Connected D-Clique (Constant Updates Per Epoch)}
+         \includegraphics[width=\textwidth]{figures/d-cliques-cifar10-scaling-fractal-cliques-cst-updates}
+         \caption{Fractal, $O(nc)$ edges}
+     \end{subfigure}  
+
+     
+     % To regenerate the figure, from directory results/scaling
+% python ../../../learn-topology/tools/plot_convergence.py 10/cifar10/fully-connected-cliques/all/2021-03-13-19:06:02-CET ../cifar10/clique-ring/all/2021-03-10-11:58:43-CET 1000/cifar10/clique-ring/all/2021-03-14-09:55:24-CET  --labels '10 nodes bsz=200' '100 nodes bsz=20' '1000 nodes bsz=2'  --legend 'lower right' --yaxis test-accuracy --save-figure ../../figures/d-cliques-cifar10-scaling-clique-ring-cst-updates.png --add-min-max
+         \begin{subfigure}[b]{0.7\textwidth}
+         \centering
+         \includegraphics[width=\textwidth]{figures/d-cliques-cifar10-scaling-clique-ring-cst-updates}
+         \caption{Ring, $O(n)$ edges}
+     \end{subfigure}  
+     
+     \caption{\label{fig:d-cliques-cifar10-scaling-fully-connected} CIFAR10: D-Clique Scaling Behaviour, where $n$ is the number of nodes, and $c$ the size of a clique (Constant Updates per Epoch).}
      \end{figure}
+     
 
 
 \subsection{Comparison to similar topologies}
@@ -432,7 +460,10 @@ In addition, it is important that all nodes are initialized with the same model
 Similar number of maximum hops but no or less clustering than D-Cliques (and no unbiasing of gradient).
 
 \begin{itemize}
-    \item Choice of 10 random neighbours (static) in a fully connected graph (D-PSGD aléatoire)
+    \item Choice of 10 random neighbours (static) in a fully connected graph (D-PSGD aléatoire), such that all nodes have at most 10 edges
+    \item 10 random neighbours, such that all nodes have at most 10 edges, but all nodes have neighbours of all classes
+    \item item previous, with neighbour averaging
+    \item item previous, with neighbour averaging and uniform initialization
     %\item Uniform Diverse Neighbourhood with No Clustering
     %\item Random network
     %\item Random Small-World Graph