diff --git a/figures/d-cliques-mnist-scaling-fractal-cliques-cst-updates.png b/figures/d-cliques-mnist-scaling-fractal-cliques-cst-updates.png new file mode 100644 index 0000000000000000000000000000000000000000..4167bb1096a336d1a4c67c3068cc1e0d7efaba83 Binary files /dev/null and b/figures/d-cliques-mnist-scaling-fractal-cliques-cst-updates.png differ diff --git a/figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png b/figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png index 62bdfd9ff9eb148f74a598e9f805732c86f9b7b9..9cb327a884aa33c19c09779fee4a1cb9afbb0516 100644 Binary files a/figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png and b/figures/d-cliques-mnist-scaling-fully-connected-cst-bsz.png differ diff --git a/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png b/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png index 0db2804de41c6328a00fdb77251723eaf0725fd1..1501f7a2459d301c7137131e0bbadca84e4d9219 100644 Binary files a/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png and b/figures/d-cliques-mnist-scaling-fully-connected-cst-updates.png differ diff --git a/main.tex b/main.tex index c3d0d2ad911b9c655774cbc388bf43f1765d0d5c..2342654774c8498f490c8ee369775026858034e5 100644 --- a/main.tex +++ b/main.tex @@ -312,13 +312,21 @@ We solve this problem by decoupling the gradient averaging from the weight avera % \end{subfigure} % 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/2021-03-12-09:13:28-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-mnist-scaling-fully-connected-cst-updates.png --ymin 80 --add-min-max +% 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} \end{subfigure} + + % To regenerate the figure, from directory results/scaling +% python ../../../learn-topology/tools/plot_convergence.py 10/mnist/clique-ring/all/2021-03-13-18:22:01-CET ../mnist/fully-connected-cliques/all/2021-03-10-10:19:44-CET 1000/mnist/fractal-cliques/all/2021-03-14-17:41:59-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-fractal-cliques-cst-updates.png --ymin 80 --add-min-max + \begin{subfigure}[b]{0.7\textwidth} + \centering + \includegraphics[width=\textwidth]{figures/d-cliques-mnist-scaling-fractal-cliques-cst-updates} + \caption{Fractal} + \end{subfigure} % To regenerate the figure, from directory results/scaling @@ -332,9 +340,7 @@ We solve this problem by decoupling the gradient averaging from the weight avera \caption{\label{fig:d-cliques-mnist-scaling-fully-connected} MNIST: D-Clique Scaling Behaviour (Constant Updates per Epoch)} \end{figure} -Show scaling effect for 10, 100, 1000 nodes (with decreasing sample sizes) for Clique Ring, Hierarchical, Fully-Connected. - -(Smallworld?) +Show scaling effect for 10, 100, 1000 nodes (with decreasing sample sizes) for Clique Ring, Fractal, Fully-Connected. Robustness to not having fully-connected cliques (static and dynamic subsets).