Search Results for author:
Found 7 papers, 0 papers with code
Transformer-Aided Semantic Communications
The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of input data.
Deep Learning-Based Real-Time Quality Control of Standard Video Compression for Live Streaming
The encoded bitrate and the quality of the compressed video depend on encoder parameters, specifically, the quantization parameter (QP).
Deep Learning-Based Real-Time Rate Control for Live Streaming on Wireless Networks
The objective is to maintain an encoded video bitrate slightly below the available channel bitrate.
Semantic Multi-Resolution Communications
The experiment with both datasets illustrates that our proposed method is capable of surpassing the SSCC method in reconstructing data with different resolutions, enabling the extraction of semantic features with heightened confidence in successive layers.
Personalized Decentralized Multi-Task Learning Over Dynamic Communication Graphs
Our algorithm uses exchanged gradients to calculate the correlations among tasks automatically, and dynamically adjusts the communication graph to connect mutually beneficial tasks and isolate those that may negatively impact each other.
Hierarchical Over-the-Air FedGradNorm
MTL can be integrated into a federated learning (FL) setting if tasks are distributed across clients and clients have a single shared network, leading to personalized federated learning (PFL).
FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task Learning
In federated settings, the statistical heterogeneity due to different task complexities and data heterogeneity due to non-iid nature of local datasets can both degrade the learning performance of the system.
