Adversarial Active Learning for Deep Networks: a Margin Based Approach

By Mélanie Ducoffe, Frédéric Precioso. arXiv.org, 2018

328 citations recorded by the source corpus.

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to rely on adversarial examples. We do not consider anymore them as a threat instead we exploit the information they provide on the distribution of the input space in order to approximate the distance to decision boundaries. We demonstrate empirically that adversarial active queries yield faster convergence of CNNs trained on MNIST, the Shoe-Bag and the Quick-Draw datasets.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/114c1ed1ae2e2a4b3d775c5a55d2c916f9d85972

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds (2019, methodology): “…the model parameters, and develop information-based uncertainty reduction criteria; inspired by recent advances on adversarial examples generation, Ducoffe and Precioso (2018) use the distance between an example and one of its adversarial examples as an approximation of its distance to the…”
A Survey of Deep Active Learning (2020, methodology): “For example, [192] and [57] point out that diversity-based methods have always been better than uncertainty-based methods, and that uncertainty-based methods perform worse than RSB; however, the latest research of [245] shows that this is not the case.”
Are All Training Examples Created Equal? An Empirical Study (2018, background): “Recent work suggests that active learning may be possible in the deep neural network setting [18, 4, 7].”
MixTrain: Scalable Training of Formally Robust Neural Networks (2018, methodology): “Recent works have trained neural network models to be adversarially robust against specific attacks [22], [23], [24], [25] launched by non-adaptive adversaries using known attacks.”