ﻻ يوجد ملخص باللغة العربية
Multi-task learning (MTL) is an important subject in machine learning and artificial intelligence. Its applications to computer vision, signal processing, and speech recognition are ubiquitous. Although this subject has attracted considerable attention recently, the performance and robustness of the existing models to different tasks have not been well balanced. This article proposes an MTL model based on the architecture of the variational information bottleneck (VIB), which can provide a more effective latent representation of the input features for the downstream tasks. Extensive observations on three public data sets under adversarial attacks show that the proposed model is competitive to the state-of-the-art algorithms concerning the prediction accuracy. Experimental results suggest that combining the VIB and the task-dependent uncertainties is a very effective way to abstract valid information from the input features for accomplishing multiple tasks.
We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations. Unlike the traditional methods where the hard labels are usually used for the classification task, we refine the
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt the label information from source domain, most existing methods employ
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess inform
Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical, since a discri
The main challenge for domain generalization (DG) is to overcome the potential distributional shift between multiple training domains and unseen test domains. One popular class of DG algorithms aims to learn representations that have an invariant cau