diff --git a/figures/d-cliques-mnist-scaling-fully-connected.png b/figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png
similarity index 100%
rename from figures/d-cliques-mnist-scaling-fully-connected.png
rename to figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png
diff --git a/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png b/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png
new file mode 100644
index 0000000000000000000000000000000000000000..317a815a7d9ad606cec5c5123ce345199043a8b6
Binary files /dev/null and b/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png differ
diff --git a/main.tex b/main.tex
index 954455ee5f38da60b748fcb75f0c741c3f1c886c..70cb15ebe5d0399a364852a3d3592999a556b88f 100644
--- a/main.tex
+++ b/main.tex
@@ -253,34 +253,37 @@ We solve this problem by decoupling the gradient averaging from the weight avera
\end{algorithmic}
\end{algorithm}
-
-
\section{Evaluation}
\subsection{MNIST and Linear Model}
\begin{figure}[htbp]
\centering
-% 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 fully-connected/all/2021-03-10-09:25:19-CET clique-ring/all/2021-03-10-10:15:24-CET fully-connected-cliques/all/2021-03-10-10:19:44-CET --add-min-max --yaxis training-loss --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 'upper right' --save-figure ../../figures/d-cliques-mnist-vs-1-node-training-loss.png
-% \begin{subfigure}[b]{0.70\textwidth}
-% \centering
-% \includegraphics[width=\textwidth]{figures/d-cliques-mnist-vs-1-node-training-loss}
-%\caption{\label{fig:d-cliques-mnist-training-loss} Training Loss}
-% \end{subfigure}
+
% 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 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
- %\begin{subfigure}[b]{\textwidth}
- %\centering
+ \centering
\includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-vs-1-node-test-accuracy}
-%\caption{\label{fig:d-cliques-mnist-linear} D-Cliques with Linear Model on MNIST.}
- %\end{subfigure}
-\caption{\label{fig:d-cliques-mnist-linear} D-Cliques with Linear Model on MNIST.}
-\end{figure}
+ \caption{\label{fig:d-cliques-mnist-linear-w-clique-averaging-w-initial-averaging} MNIST: D-Cliques Convergence Speed}
+ \end{figure}
-With and without clique averaging.
+
+
+ \begin{figure}[htbp]
+ \centering
+ \begin{subfigure}[b]{0.48\textwidth}
+ \centering
+ %\includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-vs-1-node-test-accuracy}
+ \caption{\label{fig:mnist-init-clique-avg-effect-ring} Ring}
+ \end{subfigure}
+ \begin{subfigure}[b]{0.48\textwidth}
+ \centering
+ %\includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-vs-1-node-test-accuracy}
+ \caption{\label{fig:mnist-init-clique-avg-effect-fcc} Fully-Connected-Cliques}
+ \end{subfigure}
+\caption{\label{fig:d-cliques-mnist-initialization-effect} MNIST: Effects of Clique Averaging and Uniform Initialization on Convergence Speed.}
+\end{figure}
-TODO: Update figure with actual Clique-Ring results
\subsection{CIFAR10 and Convolutional Model}
@@ -331,17 +334,22 @@ Similar number of maximum hops but no or less clustering than D-Cliques (and no
\subsection{Effect of Scaling}
-% 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.png --ymin 80 --add-min-max
+
\begin{figure}[htbp]
\centering
- \begin{subfigure}[b]{\textwidth}
+ % 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}
\centering
- \includegraphics[width=0.7\textwidth]{figures/d-cliques-mnist-scaling-fully-connected}
+ \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fully-connected-cst-bsz}
\caption{Constant Batch-Size}
\end{subfigure}
- \begin{subfigure}[b]{\textwidth}
+ % 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/2021-03-10-16:44:35-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
+\hfill
+ \begin{subfigure}[b]{0.48\textwidth}
\centering
+ \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fully-connected-cst-updates}
\caption{Constant Nb Updates per Epoch}
\end{subfigure}
\caption{\label{fig:d-cliques-mnist-scaling-fully-connected} Scaling Behaviour of Fully-Connected D-Clique}
diff --git a/results/mnist/no-clique-avg/clique-ring/experiments.sh b/results/mnist/no-clique-avg/clique-ring/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..1bf90baf4d089d037a91f926983f283e5bdf0cb4
--- /dev/null
+++ b/results/mnist/no-clique-avg/clique-ring/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology clique-ring --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear --initial-averaging
+ done;
+done;
+
diff --git a/results/mnist/no-clique-avg/fully-connected-cliques/experiments.sh b/results/mnist/no-clique-avg/fully-connected-cliques/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..67f547fd215a9c8222017a9ef8b9c30926dbc953
--- /dev/null
+++ b/results/mnist/no-clique-avg/fully-connected-cliques/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology fully-connected-cliques --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear --initial-averaging
+ done;
+done;
+
diff --git a/results/mnist/no-init-no-clique-avg/clique-ring/experiments.sh b/results/mnist/no-init-no-clique-avg/clique-ring/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..4ffcd299614b64aa594c88b00b0bef8ccf2f8b7a
--- /dev/null
+++ b/results/mnist/no-init-no-clique-avg/clique-ring/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology clique-ring --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear
+ done;
+done;
+
diff --git a/results/mnist/no-init-no-clique-avg/fully-connected-cliques/experiments.sh b/results/mnist/no-init-no-clique-avg/fully-connected-cliques/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..a20fd4d0d412de9845f3ff0ebf454e5ce241aaf8
--- /dev/null
+++ b/results/mnist/no-init-no-clique-avg/fully-connected-cliques/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology fully-connected-cliques --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear
+ done;
+done;
+
diff --git a/results/mnist/no-init/clique-ring/experiments.sh b/results/mnist/no-init/clique-ring/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..acb22fdb234921b5dd8653295fdb99d4e16a88ec
--- /dev/null
+++ b/results/mnist/no-init/clique-ring/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology clique-ring --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear --clique-gradient
+ done;
+done;
+
diff --git a/results/mnist/no-init/fully-connected-cliques/experiments.sh b/results/mnist/no-init/fully-connected-cliques/experiments.sh
new file mode 100755
index 0000000000000000000000000000000000000000..1bb88fdd8839c591f2d59daf924e588db9c8e60f
--- /dev/null
+++ b/results/mnist/no-init/fully-connected-cliques/experiments.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+TOOLS=../../../../learn-topology/tools; CWD="$(pwd)"; cd $TOOLS
+BSZS='
+ 128
+ '
+LRS='
+ 0.1
+ '
+for BSZ in $BSZS;
+ do for LR in $LRS;
+ do python sgp-mnist.py --nb-nodes 100 --nb-epochs 100 --local-classes 1 --seed 1 --nodes-per-class 10 10 10 10 10 10 10 10 10 10 --global-train-ratios 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 0.802568 --dist-optimization d-psgd --topology fully-connected-cliques --metric dissimilarity --learning-momentum 0. --sync-per-mini-batch 1 --results-directory $CWD/all --learning-rate $LR --batch-size $BSZ "$@" --parallel-training --nb-workers 10 --dataset mnist --model linear --clique-gradient
+ done;
+done;
+