Gradient Adversarial Training of Neural Networks

By Ayan Sinha, Zhao Chen, Vijay Badrinarayanan, Andrew Rabinovich. 2018

41 citations recorded by the source corpus.

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this consistency using an auxiliary network that classifies the origin of the gradient tensor, and the main network serves as an adversary to the auxiliary network in addition to performing standard task-based training. We demonstrate gradient adversarial training for three different scenarios: (1) as a defense to adversarial examples we classify gradient tensors and tune them to be agnostic to the class of their corresponding example, (2) for knowledge distillation, we do binary classification of gradient tensors derived from the student or teacher network and tune the student gradient tensor to mimic the teacher's gradient tensor; and (3) for multi-task learning we classify the gradient tensors derived from different task loss functions and tune them to be statistically indistinguishable. For each of the three scenarios we show the potential of gradient adversarial training procedure. Specifically, gradient adversarial training increases the robustness of a network to adversarial attacks, is able to better distill the knowledge from a teacher network to a student network compared to soft targets, and boosts multi-task learning by aligning the gradient tensors derived from the task specific loss functions. Overall, our experiments demonstrate that gradient tensors contain latent information about whatever tasks are being trained, and can support diverse machine learning problems when intelligently guided through adversarialization using a auxiliary network.

Subfields: Artificial Intelligence

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

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference (2020, methodology): “Several works proposed to dynamically re-weight the loss function of each task [6, 21, 55, 52], sort the order of task learning [16], or adapt the feature sharing between ‘related’ and ‘unrelated’ tasks [65], to mitigate the effect of negative transfer.”
Adversarial Robustness with Semi-Infinite Constrained Learning (2021, background): “[30] Ayan Sinha, Zhao Chen, Vijay Badrinarayanan, and Andrew Rabinovich.”
Gradients as Features for Deep Representation Learning (2020, background): “…more recently for generating adversarial samples (Szegedy et al., 2013), crafting defense strategies (Goodfellow et al., 2015), facilitating knowledge distillation (Sinha et al., 2018; Srinivas & Fleuret, 2018), and boosting multi-task and meta learning (Sinha et al., 2018; Achille et al., 2019).”
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning (2020, methodology): “[41] tried to balance the losses by adapting the gradients magnitude, but differently, they employed adversarial training to this end.”
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout (2020, background): “To generally address such issues, deep multitask learning studies properties of models with multiple outputs and has given birth to methods to balance relative gradient magnitudes [3, 17] or tune the full gradient tensor [38].”
Adversarial Examples on Object Recognition (2020, background): “Statistical Detection [67] Guard - Adversarial Detector * ** ** ** Binary Classification [62] Guard - Adversarial Detector * ** * * In-Layer Detection [117] Guard - Adversarial Detector * ** *** ** Detecting from Artifacts [52] Guard - Adversarial Detector * ** ** ** SafetyNet [111] Guard - Adversar”
Attentive Single-Tasking of Multiple Tasks (2019, methodology): “A concurrent work [60] has independently proposed this idea.”
Multi-Task Learning with Deep Neural Networks: A Survey (2020, background): “Gradient Adversarial Training (GREAT) (Sinha et al., 2018) explicitly enforces this condition by including an adversarial loss term that encourages gradients from different sources to have statistically indistinguishable distributions.”