Mingxue Liao
YOU?
Author Swipe
View article: DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning
DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning Open
Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high …
View article: FCT: An Adaptive Model for Classification of Mixed Radio Signals
FCT: An Adaptive Model for Classification of Mixed Radio Signals Open
In recent years, radio signal classification has become a hot topic in the field of wireless communication. However, current algorithms have low classification accuracy at low signal-to-noise radio (SNR) signals, and under this condition, …
View article: Replication Data for: relative errors of data relation uncertainty due to data uncertainty
Replication Data for: relative errors of data relation uncertainty due to data uncertainty Open
The data are for replication data for relative errors of data relation uncertainty due to data uncertainty. The relative errors are between data relation uncertainty estimated by theory in our paper and data relation uncertainty randomly g…
View article: Self-Adaptive Task Allocation for Decentralized Deep Learning in Heterogeneous Environments
Self-Adaptive Task Allocation for Decentralized Deep Learning in Heterogeneous Environments Open
The demand for large-scale deep learning is increasing, and distributed training is the current mainstream solution.Decentralized algorithms are widely used in distributed training.However, in a heterogeneous environment, each worker compu…
View article: The Modified Gravitation-based Algorithm for Community Detecting in Dynamic Social Networks
The Modified Gravitation-based Algorithm for Community Detecting in Dynamic Social Networks Open
With in-depth research on the complex network, people have a deeper understanding of the physical significance and mathematical characteristics of social networks. Communities are clusters of closely connected nodes within a social network…
View article: Task allocation for decentralized training in heterogeneous environment
Task allocation for decentralized training in heterogeneous environment Open
The demand for large-scale deep learning is increasing, and distributed training is the current mainstream solution. Ring AllReduce is widely used as a data parallel decentralized algorithm. However, in a heterogeneous environment, each wo…
View article: On Optimal Number of Cognitive Radios Considering Co-site Electromagnetic Compatibility
On Optimal Number of Cognitive Radios Considering Co-site Electromagnetic Compatibility Open
Cognitive radio is becoming one of the most important techniques for high utility of spectrum holes. If the holes available to cognitive users are abundant over a certain time, it is a worth consideration to increase network throughputs by…
View article: The Gravitation-based Algorithm for Community Detecting in Large-scale Social Networks
The Gravitation-based Algorithm for Community Detecting in Large-scale Social Networks Open
Communities are clusters of closely connected nodes in a social network. Detecting community structure can help us understand their network characteristics. Most popular algorithms are based on modularity optimization, such as the SLM algo…