nWordsShortDocs = 5 # Docs with less than this number of words are discarded
nEdges = 16 # Minimum number of edges per vertex in the graph
distMetric = 'cosine' # Similarity measure between graph embedded features to
# build the adjacency matrix
nDataSplits = 10 # Number of data realizations
# Obs.: The built graph depends on the split between training and validation.
# Therefore, we will run several of these splits and average across
# them, to obtain some result that is more robust to this split.
#\\\ Save values:
writeVarValues(
varsFile, {
'ratioValid': ratioValid,
'nWords': nWords,
'nWordsShortDocs': nWordsShortDocs,
'nEdges': nEdges,
'distMetric': distMetric,
'nDataSplits': nDataSplits,
'useGPU': useGPU
})
############
# TRAINING #
############
#\\\ Individual model training options
trainer = 'ADAM' # Options: 'SGD', 'ADAM', 'RMSprop'
learningRate = 0.001 # In all options
beta1 = 0.9 # beta1 if 'ADAM', alpha if 'RMSprop'
beta2 = 0.999 # ADAM option only
perturbationEpsilon = signalPower * np.arange(
1, nSimPoints + 1) / float(nSimPoints)
# Value epsilon of the perturbation, it is relative to the signal power
# and it goes from 1/nSimPoints to 1
nPerturbationRealizations = 10 # Number of realizations of the perturbation
# Each perturbation is random, so how many different perturbations we want
# to run before we average the results
nGraphRealizations = 10 # Number of graph realizations
# Each graph is random, so how many graphs to create to average the results
# The randomization of the graphs is the one that is plotted as error bars
# (i.e. how much the performance changes with different graphs within
# the same family)
#\\\ Save values:
writeVarValues(varsFile, {'nNodes': nNodes, 'graphType': graphType})
writeVarValues(varsFile, graphOptions)
writeVarValues(
varsFile, {
'nTest': nTest,
'nSimPoints': nSimPoints,
'signalPower': signalPower,
'nPerturbationRealizations': nPerturbationRealizations,
'nGraphRealizations': nGraphRealizations
})
#################
# ARCHITECTURES #
#################
# Select which wavelets to use
forceConnected = False # If True returns the largest connected component of the
# graph as the main graph ---> TRUE
kNN = 10 # Number of nearest neighbors
maxDataPoints = None # None to consider all data points
#\\\ Save values:
writeVarValues(
varsFile, {
'labelID': labelID,
'graphType': graphType,
'ratioTrain': ratioTrain,
'ratioValid': ratioValid,
'maxNodes': maxNodes,
'minRatings': minRatings,
'interpolateRatings': interpolateRatings,
'nDataSplits': nDataSplits,
'keepIsolatedNodes': keepIsolatedNodes,
'forceUndirected': forceUndirected,
'forceConnected': forceConnected,
'kNN': kNN,
'maxDataPoints': maxDataPoints,
'useGPU': useGPU
})
############
# TRAINING #
############
#\\\ Individual model training options
optimAlg = 'ADAM' # Options: 'SGD', 'ADAM', 'RMSprop'
# Every training excerpt has a WAN associated to it. We combine all these WANs
# into a single graph to use as the supporting graph for all samples. This
# combination happens under some extra options:
graphNormalizationType = 'rows' # or 'cols' - Makes all rows add up to 1.
keepIsolatedNodes = False # If True keeps isolated nodes
forceUndirected = True # If True forces the graph to be undirected (symmetrizes)
forceConnected = True # If True removes nodes (from lowest to highest degree)
# until the resulting graph is connected.
# \\\ Save values:
writeVarValues(
varsFile, {
'nClasses': nClasses,
'ratioTrain': ratioTrain,
'ratioValid': ratioValid,
'nDataSplits': nDataSplits,
'graphNormalizationType': graphNormalizationType,
'keepIsolatedNodes': keepIsolatedNodes,
'forceUndirected': forceUndirected,
'forceConnected': forceConnected
})
############
# TRAINING #
############
# \\\ Individual model training options
trainer = 'ADAM' # Options: 'SGD', 'ADAM', 'RMSprop'
learningRate = 0.001 # In all options
beta1 = 0.9 # beta1 if 'ADAM', alpha if 'RMSprop'
beta2 = 0.999 # ADAM option only
# How to process the loaded Facebook graph
keepIsolatedNodes = False # If True keeps isolated nodes
forceConnected = True # If True removes nodes (from lowest to highest degree)
# until the resulting graph is connected.
use234 = True # Use a smaller 234-matrix with 2-communities instead of the full
# graph with around 4k users
#\\\ Save values:
writeVarValues(
varsFile, {
'nClasses': nClasses,
'beginProbEdgeFailSim': beginProbEdgeFailSim,
'endProbEdgeFailSim': endProbEdgeFailSim,
'nSimPoints': nSimPoints,
'nTrain': nTrain,
'nValid': nValid,
'nTest': nTest,
'nEdgeFailRealizations': nEdgeFailRealizations,
'keepIsolatedNodes': keepIsolatedNodes,
'forceConnected': forceConnected,
'use234': use234,
'useGPU': useGPU
})
#################
# ARCHITECTURES #
#################
# Select which wavelets to use
doDiffusion = False # F. Gama, A. Ribeiro, and J. Bruna, "Diffusion scattering
# transforms on graphs," in 7th Int. Conf. Learning Representations. New
# into a single graph to use as the supporting graph for all samples. This
# combination happens under some extra options:
graphNormalizationType = 'rows' # or 'cols' - Makes all rows add up to 1.
keepIsolatedNodes = False # If True keeps isolated nodes
forceUndirected = True # If True forces the graph to be undirected (symmetrizes)
forceConnected = True # If True removes nodes (from lowest to highest degree)
# until the resulting graph is connected.
#\\\ Save values:
writeVarValues(
varsFile, {
'authorName': authorName,
'nClasses': nClasses,
'ratioTrain': ratioTrain,
'ratioValid': ratioValid,
'nDataSplits': nDataSplits,
'graphNormalizationType': graphNormalizationType,
'keepIsolatedNodes': keepIsolatedNodes,
'forceUndirected': forceUndirected,
'forceConnected': forceConnected,
'useGPU': useGPU
})
############
# TRAINING #
############
#\\\ Individual model training options
trainer = 'ADAM' # Options: 'SGD', 'ADAM', 'RMSprop'
learningRate = 0.005 # In all options
beta1 = 0.9 # beta1 if 'ADAM', alpha if 'RMSprop'
# accounting for random data generation through several nTrain or nTest.
# How to process the loaded Facebook graph
keepIsolatedNodes = False # If True keeps isolated nodes
forceConnected = True # If True removes nodes (from lowest to highest degree)
# until the resulting graph is connected.
use234 = True # Use a smaller 234-matrix with 2-communities instead of the full
# graph with around 4k users
#\\\ Save values:
writeVarValues(varsFile,
{'nClasses': nClasses,
'beginProbEdgeFailSim': beginProbEdgeFailSim,
'endProbEdgeFailSim': endProbEdgeFailSim,
'nSimPoints': nSimPoints,
'nTrain': nTrain,
'nValid': nValid,
'nTest': nTest,
'nEdgeFailRealizations': nEdgeFailRealizations,
'keepIsolatedNodes': keepIsolatedNodes,
'forceConnected': forceConnected,
'use234': use234})
#################
# ARCHITECTURES #
#################
# Select which wavelets to use
doDiffusion = True # F. Gama, A. Ribeiro, and J. Bruna, "Diffusion scattering
# transforms on graphs,” in Int. Conf. Learning Representations 2019.
# New Orleans, LA: Assoc. Comput. Linguistics, 6-9 May 2019.
doMonicCubic = True # Eq. (65) in D. K. Hammond, P. Vandergheynst, and
graphOptions = {} # Dictionary of options to pass to the createGraph function
if graphType == 'SBM':
graphOptions['nCommunities'] = nClasses # Number of communities
graphOptions['probIntra'] = 0.8 # Intracommunity probability
graphOptions['probInter'] = 0.2 # Intercommunity probability
elif graphType == 'SmallWorld':
graphOptions['probEdge'] = 0.5 # Edge probability
graphOptions['probRewiring'] = 0.1 # Probability of rewiring
elif graphType == 'geometric':
graphOptions['pos'] = [None]
graphOptions['kernelType'] = 'exponential'
graphOptions['sparseType'] = 'NN'
graphOptions['sparseParam'] = 5
#\\\ Save values:
writeVarValues(varsFile, {'nNodes': nNodes, 'graphType': graphType})
writeVarValues(varsFile, graphOptions)
writeVarValues(
varsFile, {
'nTrain': nTrain,
'nValid': nValid,
'nTest': nTest,
'tMax': tMax,
'nDataRealizations': nDataRealizations,
'nGraphRealizations': nGraphRealizations,
'nClasses': nClasses,
'useGPU': useGPU
})
############
# TRAINING #
# Every training excerpt has a WAN associated to it. We combine all these WANs
# into a single graph to use as the supporting graph for all samples. This
# combination happens under some extra options:
graphNormalizationType = 'rows' # or 'cols' - Makes all rows add up to 1.
keepIsolatedNodes = False # If True keeps isolated nodes
forceUndirected = True # If True forces the graph to be undirected (symmetrizes)
forceConnected = True # If True keeps the largest connected component
#\\\ Save values:
writeVarValues(
varsFile, {
'authorName': authorName,
'nClasses': nClasses,
'beginRatioTrainSim': beginRatioTrainSim,
'endRatioTrainSim': endRatioTrainSim,
'nSimPoints': nSimPoints,
'ratioValid': ratioValid,
'nDataSplits': nDataSplits,
'graphNormalizationType': graphNormalizationType,
'keepIsolatedNodes': keepIsolatedNodes,
'forceUndirected': forceUndirected,
'forceConnected': forceConnected
})
#################
# ARCHITECTURES #
#################
# Select which wavelets to use
doDiffusion = True # F. Gama, A. Ribeiro, and J. Bruna, "Diffusion scattering
# transforms on graphs,” in Int. Conf. Learning Representations 2019.
# New Orleans, LA: Assoc. Comput. Linguistics, 6-9 May 2019.
