Meta-Tasks: An alternative view on Meta-Learning Regularization

no code implementations • 27 Feb 2024 • Mohammad Rostami, Atik Faysal, Huaxia Wang, Avimanyu Sahoo, Ryan Antle

The ability to generalize effectively on both novel and training tasks is a significant barrier to FSL.

Few-Shot Learning

Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning

1 code implementation • 19 Oct 2023 • Atik Faysal, Mohammad Rostami, Huaxia Wang, Avimanyu Sahoo, Ryan Antle

We use augmented samples as the query set during the training phase of the unsupervised meta-learning.

Few-Shot Learning Relation Network +2

A Robust Adversarial Network-Based End-to-End Communications System With Strong Generalization Ability Against Adversarial Attacks

1 code implementation • 3 Mar 2021 • Yudi Dong, Huaxia Wang, Yu-Dong Yao

We propose a novel defensive mechanism based on a generative adversarial network (GAN) framework to defend against adversarial attacks in end-to-end communications systems.

Generative Adversarial Network

Channel Estimation for One-Bit Multiuser Massive MIMO Using Conditional GAN

2 code implementations • 19 Jun 2020 • Yudi Dong, Huaxia Wang, Yu-Dong Yao

Channel estimation is a challenging task, especially in a massive multiple-input multiple-output (MIMO) system with one-bit analog-to-digital converters (ADC).

A Direct Approach to Robust Deep Learning Using Adversarial Networks

1 code implementation • ICLR 2019 • Huaxia Wang, Chun-Nam Yu

We model the adversarial noise using a generative network, trained jointly with a classification discriminative network as a minimax game.

General Classification Generative Adversarial Network +1