How do I implement multilabel classification neural network with keras

Question

I am attempting to implement a neural network using Keras with a problem that involves multilabel classification. I understand that one way to tackle the problem is to transform it to several binary classification problems. I have implemented one of these, but am not sure how to proceed with the others, mostly how do I go about combining them? My data set has 5 input variables and 5 labels. Generally a single sample of data would have 1-2 labels. It is rare to have more than two labels.

Here is my code (thanks to machinelearningmastery.com):

import numpy
import pandas
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import StratifiedKFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline


# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)


# load dataset
dataframe = pandas.read_csv("Realdata.csv", header=None)
dataset = dataframe.values
# split into input (X) and output (Y) variables
X = dataset[:,0:5].astype(float)
Y = dataset[:,5]


# encode class values as integers
encoder = LabelEncoder()
encoder.fit(Y)
encoded_Y = encoder.transform(Y)


# baseline model
def create_baseline():
    # create model
    model = Sequential()
    model.add(Dense(5, input_dim=5, kernel_initializer='normal', activation='relu'))
    model.add(Dense(1, kernel_initializer='normal', activation='sigmoid'))
    # Compile model
    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
    scores = model.evaluate(X, encoded_Y)
    print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
    #Make predictions....change the model.predict to whatever you want instead of X
    predictions = model.predict(X)
    # round predictions
    rounded = [round(x[0]) for x in predictions]
    print(rounded)
    return model
    

# evaluate model with standardized dataset
estimator = KerasClassifier(build_fn=create_baseline, epochs=100, batch_size=5, verbose=0)
kfold = StratifiedKFold(n_splits=10, shuffle=True, random_state=seed)
results = cross_val_score(estimator, X, encoded_Y, cv=kfold)
print("Results: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))

Answer 1

The approach you are referring to is the one-versus-all or the one-versus-one strategy for multi-label classification. However, when using a neural network, the easiest solution for a multi-label classification problem with 5 labels is to use a single model with 5 output nodes. With keras:

model = Sequential()
model.add(Dense(5, input_dim=5, kernel_initializer='normal', activation='relu'))
model.add(Dense(5, kernel_initializer='normal', activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='sgd')

You can provide the training labels as binary-encoded vectors of length 5. For instance, an example that corresponds to classes 2 and 3 would have the label [0 1 1 0 0].