• German

Main Navigation

Saadallah/Morik/2021a: Meta-Adversarial Training of Neural Networks for Binary Classification

Bibtype Inproceedings
Bibkey Saadallah/Morik/2021a
Author Saadallah, Amal and Katharina, Morik
Title Meta-Adversarial Training of Neural Networks for Binary Classification
Journal IJCNN International Joint Conference on Neural Networks
Abstract We propose a novel framework for classification
using neural networks via an adversarial training procedure,
in which we simultaneously train a main classifier—a neural
network that solves the original classification task, i.e classifying
instances into two main categories—and two meta-classifiers
which act as discriminators and aim to detect false positives
and negatives predicted by the original classifier. Our framework
operates in two stages: In a first stage, both main and meta
classifiers are pre-trained using the cross-entropy loss. The second
stage consists of an adversarial training stage in which both main
and meta classifiers are placed in a min-max game. Therefore,
we switch to our new loss function so that the goal for the
main classifier becomes to maximize the probability of failure of
the adversarial meta-classifiers. Our training procedure can be
explained by the fact that the meta-classifiers are more accurate
when the main classifier is weak i.e., instances misclassified by
the main classifier are naturally easy to separate and assign to
the correct class membership. Opposingly, if the main classifier
is robust enough, then the meta-classifiers are supposed to
distinguish between instances that are naturally hard to classify,
making thus more mistakes. In this work, both main and metaclassifiers
are defined by Multi-Layer Perceptrons (MLP) and
the entire training system is performed using backpropagation
with gradient descent optimization. Experiments demonstrate
the potential of our framework in outperforming the traditional
learning scheme in improving the classification accuracy.
Year 2021
Projekt SFB876-B3
Bibtex Here you can get this literature entry as BibTeX format.