In recent years, many model intellectual property (IP) proof methods for IP protection have
been proposed, such as model watermarking and model fingerprinting. However, with the …

Low-rank compression is an important model compression strategy for obtaining compact
neural network models. In general, because the rank values directly determine the model …

Network pruning techniques are widely employed to reduce the memory requirements and
increase the inference speed of neural networks. This work proposes a novel RNN pruning …

Despite their high accuracy, complex neural networks demand significant computational
resources, posing challenges for deployment on resource-constrained devices such as …

Model compression methods can reduce model complexity on the premise of maintaining
acceptable performance, and thus promote the application of deep neural networks under …

Federated learning has recently been proposed as a solution to the problem of using private
or sensitive data for training a central deep model, without exchanging the local data. In …

This paper has been accepted by ACM TOMM. https://dl. acm. org/doi/pdf/10.1145/3572777
In recent years, many model intellectual property (IP) proof methods for IP protection have …

This work delves into the exploration of optimizing Multilayer Perceptrons (MLP) or the
dense layers of other sorts of Deep Neural Networks when they are aimed at edge …

At present, deep neural networks (DNNs) have been widely used, and the deployment of
DNNs to resource-constrained devices becomes a popular trend, which leads to the …

Model compression methods can reduce model complexity on the premise of maintaining
acceptable performance, and thus promote the application of deep neural networks under …