[HTML][HTML] A brief review of hypernetworks in deep learning
Hypernetworks, or hypernets for short, are neural networks that generate weights for another
neural network, known as the target network. They have emerged as a powerful deep …
neural network, known as the target network. They have emerged as a powerful deep …
Domain generalization in machine learning models for wireless communications: Concepts, state-of-the-art, and open issues
Data-driven machine learning (ML) is promoted as one potential technology to be used in
next-generation wireless systems. This led to a large body of research work that applies ML …
next-generation wireless systems. This led to a large body of research work that applies ML …
A Dynamic Learning Method towards Realistic Compositional Zero-Shot Learning
X Hu, Z Wang - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
To tackle the challenge of recognizing images of unseen attribute-object compositions,
Compositional Zero-Shot Learning (CZSL) methods have been previously addressed …
Compositional Zero-Shot Learning (CZSL) methods have been previously addressed …
A Multivocal Literature Review on Privacy and Fairness in Federated Learning
B Balbierer, L Heinlein, D Zipperling, N Kühl - arXiv preprint arXiv …, 2024 - arxiv.org
Federated Learning presents a way to revolutionize AI applications by eliminating the
necessity for data sharing. Yet, research has shown that information can still be extracted …
necessity for data sharing. Yet, research has shown that information can still be extracted …
Graph Knowledge Distillation to Mixture of Experts
P Rumiantsev, M Coates - arXiv preprint arXiv:2406.11919, 2024 - arxiv.org
In terms of accuracy, Graph Neural Networks (GNNs) are the best architectural choice for the
node classification task. Their drawback in real-world deployment is the latency that …
node classification task. Their drawback in real-world deployment is the latency that …
Domain Generalization Deep Graph Transformation
Graph transformation that predicts graph transition from one mode to another is an important
and common problem. Despite much progress in developing advanced graph …
and common problem. Despite much progress in developing advanced graph …
Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation
H Honghaofu, L Zhang, B Fu, R Zhao, J Su… - Findings of the …, 2024 - aclanthology.org
The primary objective of sign language translation (SLT) is to transform sign language
videos into natural sentences. A crucial challenge in this field is developing signer …
videos into natural sentences. A crucial challenge in this field is developing signer …
[PDF][PDF] Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation
H Fu, L Zhang, B Fu, R Zhao, E Computing - aclanthology.org
The primary objective of sign language translation (SLT) is to transform sign language
videos into natural sentences. A crucial challenge in this field is developing signer …
videos into natural sentences. A crucial challenge in this field is developing signer …