Skip to content

GitLab

Commit 0045094d authored by PTSEFTON's avatar PTSEFTON
Browse files

Added GTM test data in as files rather than a referenced repo

parent b286ff5f
Expand all Hide whitespace changes
Inline Side-by-side
GTM @ 132249b4
Subproject commit 132249b4d9783ffceca13af23e189717d317b236
test_data/GTM/CATALOG.html 0 → 100644
View file @ 0045094d
<html>
<head>
<style>
table {
width: 90%;
text-align: left;
vertical-align: top;
margin-bottom: 2em;
}
td {
margin-right: 2em;
white-space: normal;
}
details {
margin-left: 2em;
}
.break {
word-break: break-all;
}
div.collection {
margin-left: +1em;
}
</style>
<script type="application/ld+json">
{
"@id": "https://doi.org/10.4225/59/59e3d6d08faa9",
"@type": [
"Dataset"
],
"contact": [
{
"@id": "http://orcid.org/0000-0002-8367-6908"
}
],
"citation": [
{
"@id": "http://dx.doi.org/10.1109/TCYB.2014.2386282"
}
],
"path": [
"./"
],
"creator": [
{
"@id": "http://orcid.org/0000-0002-8367-6908"
},
{
"@id": "http://orcid.org/0000-0003-0690-4732"
},
{
"@id": "http://orcid.org/0000-0003-3960-0583"
},
{
"@id": "https://orcid.org/0000-0002-6953-3986"
}
],
"datePublished": [
"2018-03-10"
],
"description": [
"This demo is the sampling inference for Graph Topic Model, and more details about this model can be found in the following reference: @ARTICLE{7015568, author={J. Xuan and J. Lu and G. Zhang and X. Luo}, journal={IEEE Transactions on Cybernetics}, title={Topic Model for Graph Mining}, year={2015}, volume={45}, A Markov chain Monte Carlo (MCMC) algorithm is developed and implemented to inference the Graph Topic Model (GTM). GTM is a probabilistic graphical model for the data represented by graph structure, e.g., chemical formulas or documents."
],
"hasPart": [
{
"@id": "gtm_gs.m"
},
{
"@id": "LICENSE"
},
{
"@id": "README.txt"
},
{
"@id": "test_gtm.m"
}
],
"identifier": [
"https://doi.org/10.4225/59/59e3d6d08faa9"
],
"license": [
{
"@id": "https://www.gnu.org/licenses/gpl-3.0.en.html"
}
],
"name": [
"GTM"
],
"publisher": [
"University of Technology Sydney"
]
}
</script>
<link rel="stylesheet"
href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/css/bootstrap.min.css"
integrity="sha384-BVYiiSIFeK1dGmJRAkycuHAHRg32OmUcww7on3RYdg4Va+PmSTsz/K68vbdEjh4u"
crossorigin="anonymous"/>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/4.7.0/css/font-awesome.min.css">
<meta charset='utf-8'/>
</head>
<body>
<nav class="navbar navbar-inverse">
<ul class="nav navbar-nav" >
<li >
<a href="" class="active"><button type="button" class="btn btn-default btn-sm"><span class="glyphicon glyphicon-home"></span>&nbsp;GTM</button></a></li>
</ul>
</nav>
<div class="container">
<div class="jumbotron">
<h3>GTM</h3>
<h4></h4>
</div>
<p>A machine-readable version of this page, created at 2018-09-06T23:50:26.371Z is available <a href='CATALOG.json'>CATALOG.json</a></p>
<table class = 'table' id = 'https://doi.org/10.4225/59/59e3d6d08faa9'
><hr
><tr
><th style = 'white-space: nowrap; width: 1%;'
>@id</th
><td
><a href = 'https://doi.org/10.4225/59/59e3d6d08faa9' class = 'fa fa-external-link' title = 'GTM'
>https://doi.org/10.4225/59/59e3d6d08faa9</a
></td
></tr
><tr
><th
><span
>name<sup
><a href = 'http://schema.org/name' title = 'Definition of: name'
>?</a
></sup
></span
></th
><td
><b
>GTM</b
></td
></tr
><tr
><th
>@type</th
><td
><span
>Dataset<sup
><a href = 'http://schema.org/Dataset' title = 'Definition of: Dataset'
>?</a
></sup
></span
></td
></tr
><tr
><th
><span
>description<sup
><a href = 'http://schema.org/description' title = 'Definition of: description'
>?</a
></sup
></span
></th
><td
>This demo is the sampling inference for Graph Topic Model, and more details about this model can be found in the following reference: @ARTICLE{7015568, author={J. Xuan and J. Lu and G. Zhang and X. Luo}, journal={IEEE Transactions on Cybernetics}, title={Topic Model for Graph Mining}, year={2015}, volume={45}, A Markov chain Monte Carlo (MCMC) algorithm is developed and implemented to inference the Graph Topic Model (GTM). GTM is a probabilistic graphical model for the data represented by graph structure, e.g., chemical formulas or documents.</td
></tr
><tr
><th
><span
>datePublished<sup
><a href = 'http://schema.org/datePublished' title = 'Definition of: datePublished'
>?</a
></sup
></span
></th
><td
>2018-03-10</td
></tr
><tr
><th
><span
>creator<sup
><a href = 'http://schema.org/creator' title = 'Definition of: creator'
>?</a
></sup
></span
></th
><td
><ul
><li
><a href = './CATALOG/http:__orcid.org_0000-0002-8367-6908.html'
>J. Xuan</a
></li
><li
><a href = './CATALOG/http:__orcid.org_0000-0003-0690-4732.html'
>J. Lu</a
></li
><li
><a href = './CATALOG/http:__orcid.org_0000-0003-3960-0583.html'
>G. Zhang</a
></li
><li
><a href = './CATALOG/https:__orcid.org_0000-0002-6953-3986.html'
>X. Luo</a
></li
></ul
></td
></tr
><tr
><th
><span
>path<sup
><a href = 'http://schema.org/contentUrl' title = 'Definition of: path'
>?</a
></sup
></span
></th
><td
><a href = './'
>.</a
></td
></tr
><tr
><th
><span
>contact<sup
><a href = 'http://schema.org/accountablePerson' title = 'Definition of: contact'
>?</a
></sup
></span
></th
><td
><a href = './CATALOG/http:__orcid.org_0000-0002-8367-6908.html'
>J. Xuan</a
></td
></tr
><tr
><th
><span
>citation<sup
><a href = 'http://schema.org/citation' title = 'Definition of: citation'
>?</a
></sup
></span
></th
><td
><a href = './CATALOG/http:__dx.doi.org_10.1109_TCYB.2014.2386282.html'
>Topic Model for Graph Mining</a
></td
></tr
><tr
><th
><span
>hasPart<sup
><a href = 'http://schema.org/hasPart' title = 'Definition of: hasPart'
>?</a
></sup
></span
></th
><td
><ul
><li
><a href = './CATALOG/gtm_gs.m.html'
>gtm_gs.m</a
></li
><li
><a href = './CATALOG/LICENSE.html'
>LICENSE</a
></li
><li
><a href = './CATALOG/README.txt.html'
>README.txt</a
></li
><li
><a href = './CATALOG/test_gtm.m.html'
>test_gtm.m</a
></li
></ul
></td
></tr
><tr
><th
><span
>license<sup
><a href = 'http://schema.org/license' title = 'Definition of: license'
>?</a
></sup
></span
></th
><td
><a href = './CATALOG/https:__www.gnu.org_licenses_gpl-3.0.en.html.html'
>GPL 3</a
></td
></tr
><tr
><th
><span
>publisher<sup
><a href = 'http://schema.org/publisher' title = 'Definition of: publisher'
>?</a
></sup
></span
></th
><td
>University of Technology Sydney</td
></tr
></table
>
<p>This file was created at 2018-09-06T23:50:26.381Z by
<a href='https://code.research.uts.edu.au/eresearch/calcytejs'>
Calcyte</a> which implements the <a href='https://github.com/UTS-eResearch/datacrate/blob/master/spec/0.3/data_crate_specification_v0.3.md'>
Draft DataCrate Packaging format</a>, version 0.3
</p>
</body>
</html>
test_data/GTM/CATALOG.json 0 → 100644
View file @ 0045094d
This diff is collapsed.
test_data/GTM/LICENSE 0 → 100644
View file @ 0045094d
This diff is collapsed.
test_data/GTM/README.txt 0 → 100644
View file @ 0045094d
This demo is the sampling inference for Graph Topic Model, and more details about this model can be found in the following reference:
@ARTICLE{7015568,
author={J. Xuan and J. Lu and G. Zhang and X. Luo},
journal={IEEE Transactions on Cybernetics},
title={Topic Model for Graph Mining},
year={2015},
volume={45},
number={12},
pages={2792-2803},
keywords={data mining;data structures;graph theory;pattern classification;text analysis;unsupervised learning;Bernoulli distribution;GTM;bag-of-word assumption;classification;edge modeling;graph dataset;graph mining;graph nodes;graph representation;graph supervised learning;graph-structured data;innovative graph topic model;latent Dirichlet allocation;latent topic discovery;unsupervised learning;Chemical elements;Chemicals;Data mining;Data models;Hidden Markov models;Inference algorithms;Vectors;Graph mining;latent Dirichlet allocation (LDA);topic model},
doi={10.1109/TCYB.2014.2386282},
ISSN={2168-2267},
month={Dec},}
test_data/GTM/gtm_gs.m 0 → 100644
View file @ 0045094d
% Implementation of GTM by Gibbs sampling
%
%
%
% Input:
% data.G - graph number
% data.N - node vocabulary size
% data.graphs - graph list
% K - topic number
% Output:
%
% GTM - model output
% L - Log likelihood list
%
% Random data for testing:
%
% K = 10;
% G = 100;
% V = 200;
% Ng = randi([1 10], 1, G);
% graphs = cell(G);
%
% for gi = 1 : G
% nodes = randi([1, V], 1, Ng(gi));
% edges = triu(randi([0 1], Ng(gi)));
% edges = edges + triu(edges, 1)';
%
% edges(logical(eye(Ng(gi)))) = Inf;
%
% graph.nodes = nodes;
% graph.edges = edges;
% graphs{gi} = graph;
% end
%
% data.G = G;
% data.V = V;
% data.Ng = Ng;
% data.graphs = graphs;
function [ GTM, L_list ] = gtm_gs( data, K, alpha, beta )
L_list = [];
% initialization
fprintf('----- GTM model initialization........ \n');
[G, V, Ng, graphs, theta, z, phi, phi_norm, GKC, KV, KK] = intialization(data, K, alpha, beta);
% output
phi_expc = zeros(K, V);
theta_expc = zeros(G, K);
samplenum = 0;
% start Gibbs sampling
iter_max = 1000;
burnin = 100;
inteval = 20;
it = 1;
while it <= iter_max
fprintf('----- Gibbs sampling iternum: %d \n', it);
%update z
fprintf('----- update z \n');
tic;
[z, GKC, KV, KK] = Update_z(G, K, Ng, graphs, theta, z, phi, phi_norm, GKC, KV, KK);
fprintf('----- use time: %d \n', toc);
%update theta
fprintf('----- update theta \n');
tic;
theta = Update_theta(GKC, K, alpha);
fprintf('----- use time: %d \n', toc);
%update phi
fprintf('----- update phi \n');
tic;
[phi, phi_norm] = Update_phi(phi, phi_norm, K, V, KV, KK, beta);
fprintf('----- use time: %d \n', toc);
%evaluate loglikehd
fprintf('----- evaluate logLikelihood \n');
tic;
[L] = Evaluate_likehd(phi, phi_norm, K, V, KV, KK, beta);
fprintf('----- L: %d \n', L);
fprintf('----- use time: %d \n', toc);
L_list = [L_list, L];
% collect samples
if it > burnin && rem(it, inteval) == 0
phi_expc = phi_expc + phi;
theta_expc = theta_expc + theta;
samplenum = samplenum + 1;
end
it = it + 1;
end
% output
GTM.phi = phi_expc / samplenum;
GTM.theta = theta_expc / samplenum;
end
function [G, V, Ng, graphs, theta, z, phi, phi_norm, GKC, KV, KK] = intialization(data, K, alpha, beta)
G = data.G;
V = data.V;
graphs = data.graphs;
Ng = data.Ng;
%
GKC = zeros(G, K);
KV = zeros(K, V);
KK = zeros(K, 2, K);
% z
z = cell(1, G);
k_tmp = [];
v_tmp = [];
for gi = 1:G
g = graphs{gi};
nodes_g = g.nodes;
edges_g = g.edges;
z_g = randi([1 K], 1, length(nodes_g));
z{gi} = z_g;
for k = 1 : K
idxz = find(z_g == k);
kc = length(idxz);
GKC(gi, k) = kc;
[~,link_z] = find(edges_g(idxz, :) == 1);
link_k = z_g(link_z);
[~,nolink_z] = find(edges_g(idxz, :) == 0);
nolink_k = z_g(nolink_z);
if ~isempty(link_k)
tab_link = tabulate(link_k);
k_list_tmp = tab_link(:, 1);
k_count_tmp = tab_link(:, 2);
KK(k, 1, k_list_tmp) = reshape(KK(k, 1, k_list_tmp), length(k_list_tmp), 1) + k_count_tmp ;
end
if ~isempty(nolink_k)
tab_nolink = tabulate(nolink_k);
k_list_tmp = tab_nolink(:, 1);
k_count_tmp = tab_nolink(:, 2);
KK(k, 2, k_list_tmp) = reshape(KK(k, 2, k_list_tmp), length(k_list_tmp), 1) + k_count_tmp ;
end
end
k_tmp = [k_tmp z_g];
v_tmp = [v_tmp nodes_g];
end
% theta
theta = gamrnd(alpha * ones(G, K), 1);
theta = theta ./ repmat(sum(theta, 2), 1, K);
% phi
phi = gamrnd(beta * ones(K, V), 1);
phi = phi ./ repmat(sum(phi, 2), 1, V);
phi_norm = zeros(1, K);
for k = 1 : K
v_list = zeros(1, V);
idx = find(k_tmp == k);
tab = tabulate(v_tmp(idx));
v_list(tab(:, 1)) = tab(:, 2);
KV(k, :) = v_list;
phi_norm(k) = norm(phi(k, :));
end
end
function theta = Update_theta(GKC, K, alpha)
theta = gamrnd(GKC+alpha, 1);
theta = theta ./ repmat(sum(theta, 2), 1, K);
end
function [z, GKC, KV, KK] = Update_z(G, K, Ng, graphs, theta, z, phi, phi_norm, GKC, KV, KK)
KK = zeros(K, 2, K);
k_new_ratio = 0;
%zall = sum(Ng);
for gi = 1 : G
z_g = z{gi};
g = graphs{gi};
nodes_g = g.nodes;
edges_g = g.edges;
for zi = 1 : Ng(gi)
k_old = z_g(zi);
v_zi = nodes_g(zi);
pk = log(theta(gi, :) + eps) + transp(log(phi(:, v_zi) + eps));
link_z = find(edges_g(zi, :) == 1);
link_k = z_g(link_z);
if ~isempty(link_k)
pk = pk + transpose(sum(log( (phi * phi(link_k, :)') ./ ( phi_norm' * phi_norm(link_k)) + eps), 2));
end
nolink_z = find(edges_g(zi, :) == 0);
nolink_k = z_g(nolink_z);
if ~isempty(nolink_k)
pk = pk + transpose(sum(log(1- (phi * phi(nolink_k, :)') ./ ( phi_norm' * phi_norm(nolink_k)) + eps), 2));
end
p = 1 ./ sum(exp(repmat(pk, [K 1]) - repmat(pk', [1 K])), 2);
k_new = find(mnrnd(1, p) == 1);
if k_old ~= k_new
k_new_ratio = k_new_ratio + 1;
z_g(zi) = k_new;
GKC(gi, k_old) = GKC(gi, k_old) - 1;
GKC(gi, k_new) = GKC(gi, k_new) + 1;
KV(k_old, v_zi) = KV(k_old, v_zi) - 1;
KV(k_new, v_zi) = KV(k_new, v_zi) + 1;
end
end
z{gi} = z_g;
%
for k = 1 : K
idxz = find(z_g == k);
if ~isempty(idxz)
[~,link_z] = find(edges_g(idxz, :) == 1);
link_k = z_g(link_z);
[~,nolink_z] = find(edges_g(idxz, :) == 0);
nolink_k = z_g(nolink_z);
if ~isempty(link_k)
tab_link = tabulate(link_k);
k_list_tmp = tab_link(:, 1);
k_count_tmp = tab_link(:, 2);
KK(k, 1, k_list_tmp) = reshape(KK(k, 1, k_list_tmp), length(k_list_tmp), 1) + k_count_tmp ;
end