LEARNING METHOD, LEARNING APPARATUS AND PROGRAM
A method includes receiving data including cases and labels therefor, calculating a predicted value of a label for each case included in the data using parameters of a neural network and information representing cases in which the labels are observed among the cases in the data, selecting one case from the data using parameters of another neural network and information representing the cases where the labels are observed among the cases in the data, training the parameters of the neural network using an error between the predicted value and a value of the label for each case in the data, and training the parameters of the other neural network using the error and another error between a predicted value of a label for each case when the one case is additionally observed and a value of the label for the case.
1 . A learning method, executed by a computer, comprising:
receiving data G d including cases and labels for the cases;
calculating a predicted value of a label for each case included in the data G d using parameters of a first neural network and information representing cases in which the labels are observed among the respective cases included in the data G d ;
selecting one case from the respective cases included in the data G d using parameters of a second neural network and information representing the cases in which the labels are observed among the respective cases included in the data G d ;
training the parameters of the first neural network using a first error between the predicted value and a value of the label for each case included in the data G d ; and
training the parameters of the second neural network using the first error and a second error between a predicted value of a label for each case when the one case is additionally observed and a value of the label for the case.
2 . The learning method according to claim 1 , wherein the training the parameters of the second neural network includes
training the parameters of the second neural network such that a reduction rate of the second error with respect to the first error is maximized.
3 . The learning method according to claim 1 , wherein the selecting includes
calculating a score for selecting the one case and selecting the one case in accordance with a distribution based on the score.
4 . The learning method according to claim 2 , wherein the selecting includes
calculating a score for selecting the one case and selecting the one case in accordance with a distribution based on the score.
5 . The learning method according to claim 1 , wherein the data G d is data represented in a graph format where cases are indicated as nodes, and
the first neural network and the second neural network are graph convolutional neural networks.
6 . The learning method according to claim 2 , wherein the data G d is data represented in a graph format where cases are indicated as nodes, and
the first neural network and the second neural network are graph convolutional neural networks.
7 . The learning method according to claim 3 , wherein the data G d is data represented in a graph format where cases are indicated as nodes, and
the first neural network and the second neural network are graph convolutional neural networks.
8 . The learning method according to claim 4 , wherein the data G d is data represented in a graph format where cases are indicated as nodes, and
the first neural network and the second neural network are graph convolutional neural networks.
9 . A learning apparatus comprising a processor, the processor being configured to:
receive data G d including cases and labels for the cases;
calculate a predicted value of a label for each case included in the data G d using parameters of a first neural network and information representing cases in which the labels are observed among the respective cases included in the data G d ;
select one case from the respective cases included in the data G d using parameters of a second neural network and information representing the cases in which the labels are observed among the respective cases included in the data G d ;
train the parameters of the first neural network using a first error between the predicted value and a value of the label for each case included in the data G d ; and
train the parameters of the second neural network using the first error and a second error between a predicted value of a label for each case when the one case is additionally observed and a value of the label for the case.
10 . A non-transitory computer-readable recording medium storing a program that causes a computer to
receive data G d including cases and labels for the cases;
calculate a predicted value of a label for each case included in the data G d using parameters of a first neural network and information representing cases in which the labels are observed among the respective cases included in the data G d ;
select one case from the respective cases included in the data G d using parameters of a second neural network and information representing the cases in which the labels are observed among the respective cases included in the data G d ;
train the parameters of the first neural network using a first error between the predicted value and a value of the label for each case included in the data G d ; and
train the parameters of the second neural network using the first error and a second error between a predicted value of a label for each case obtained when the one case is additionally observed and a value of the label for the case.