This paper studies the curious phenomenon for machine learning models with Transformer
architectures that their activation maps are sparse. By activation map we refer to the …

Model compression techniques are receiving increasing attention; however, the effect of
compression on model fairness is still under explored. This is the first paper to examine the …

With the growth of model and data sizes, a broad effort has been made to design pruning
techniques that reduce the resource demand of deep learning pipelines, while retaining …

Increasing the model capacity is a known approach to enhance the adversarial robustness
of deep learning networks. On the other hand, various model compression techniques …

Abstract Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance
in many computer vision tasks. However high computational and storage demands hinder …

Pruning techniques have been successfully used in neural networks to trade accuracy for
sparsity. However, the impact of network pruning is not uniform: prior work has shown that …

With the rapid development of deep learning, the sizes of deep neural networks are getting
larger beyond the affordability of hardware platforms. Given the fact that neural networks are …

Network pruning has been widely studied to reduce the complexity of deep neural networks
(DNNs) and hence speed up their inference. Unfortunately, most existing pruning methods …

Machine learning models have made significant breakthroughs across various domains.
However, it is crucial to assess these models to obtain a complete understanding of their …

Neural networks are a powerful class of non-linear functions. However, their black-box
nature makes it difficult to explain their behaviour and certify their safety. Abstraction …